add test, fix ci

Adds a hint to use ctrl-t to view transcript for more details

<img width="475" height="49" alt="image"
src="https://github.com/user-attachments/assets/6ff650eb-ed54-4699-be04-3c50f0f8f631"
/>

.github/actions/codex/bun.lock

@@ -9,7 +9,7 @@
       },
       "devDependencies": {
         "@types/bun": "^1.2.20",
-        "@types/node": "^24.2.1",
+        "@types/node": "^24.3.0",
         "prettier": "^3.6.2",
         "typescript": "^5.9.2",
       },
@@ -50,7 +50,7 @@
 
     "@types/bun": ["@types/bun@1.2.20", "", { "dependencies": { "bun-types": "1.2.20" } }, "sha512-dX3RGzQ8+KgmMw7CsW4xT5ITBSCrSbfHc36SNT31EOUg/LA9JWq0VDdEXDRSe1InVWpd2yLUM1FUF/kEOyTzYA=="],
 
-    "@types/node": ["@types/node@24.2.1", "", { "dependencies": { "undici-types": "~7.10.0" } }, "sha512-DRh5K+ka5eJic8CjH7td8QpYEV6Zo10gfRkjHCO3weqZHWDtAaSTFtl4+VMqOJ4N5jcuhZ9/l+yy8rVgw7BQeQ=="],
+    "@types/node": ["@types/node@24.3.0", "", { "dependencies": { "undici-types": "~7.10.0" } }, "sha512-aPTXCrfwnDLj4VvXrm+UUCQjNEvJgNA8s5F1cvwQU+3KNltTOkBm1j30uNLyqqPNe7gE3KFzImYoZEfLhp4Yow=="],
 
     "@types/react": ["@types/react@19.1.8", "", { "dependencies": { "csstype": "^3.0.2" } }, "sha512-AwAfQ2Wa5bCx9WP8nZL2uMZWod7J7/JSplxbTmBQ5ms6QpqNYm672H0Vu9ZVKVngQ+ii4R/byguVEUZQyeg44g=="],
 
@@ -82,6 +82,8 @@
 
     "@octokit/plugin-rest-endpoint-methods/@octokit/types": ["@octokit/types@12.6.0", "", { "dependencies": { "@octokit/openapi-types": "^20.0.0" } }, "sha512-1rhSOfRa6H9w4YwK0yrf5faDaDTb+yLyBUKOCV4xtCDB5VmIPqd/v9yr9o6SAzOAlRxMiRiCic6JVM1/kunVkw=="],
 
+    "bun-types/@types/node": ["@types/node@24.2.1", "", { "dependencies": { "undici-types": "~7.10.0" } }, "sha512-DRh5K+ka5eJic8CjH7td8QpYEV6Zo10gfRkjHCO3weqZHWDtAaSTFtl4+VMqOJ4N5jcuhZ9/l+yy8rVgw7BQeQ=="],
+
     "@octokit/plugin-paginate-rest/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],
 
     "@octokit/plugin-rest-endpoint-methods/@octokit/types/@octokit/openapi-types": ["@octokit/openapi-types@20.0.0", "", {}, "sha512-EtqRBEjp1dL/15V7WiX5LJMIxxkdiGJnabzYx5Apx4FkQIFgAfKumXeYAqqJCj1s+BMX4cPFIFC4OLCR6stlnA=="],

.github/actions/codex/package.json

@@ -14,7 +14,7 @@
     },
     "devDependencies": {
         "@types/bun": "^1.2.20",
-        "@types/node": "^24.2.1",
+        "@types/node": "^24.3.0",
         "prettier": "^3.6.2",
         "typescript": "^5.9.2"
     }

.github/dependabot.yaml

@@ -24,3 +24,7 @@ updates:
     directory: /
     schedule:
       interval: weekly
+  - package-ecosystem: rust-toolchain
+    directory: codex-rs
+    schedule:
+      interval: weekly

.github/dotslash-config.json

@@ -17,6 +17,10 @@
         "linux-aarch64": {
           "regex": "^codex-aarch64-unknown-linux-musl\\.zst$",
           "path": "codex"
+        },
+        "windows-x86_64": {
+          "regex": "^codex-x86_64-pc-windows-msvc\\.exe\\.zst$",
+          "path": "codex.exe"
         }
       }
     }

.github/workflows/ci.yml

@@ -12,7 +12,7 @@ jobs:
       NODE_OPTIONS: --max-old-space-size=4096
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Setup Node.js
         uses: actions/setup-node@v4

.github/workflows/codespell.yml

@@ -18,7 +18,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
       - name: Annotate locations with typos
         uses: codespell-project/codespell-problem-matcher@b80729f885d32f78a716c2f107b4db1025001c42 # v1
       - name: Codespell

.github/workflows/codex.yml

@@ -37,9 +37,9 @@ jobs:
       #    Codex is not going to run.
 
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
-      - uses: dtolnay/rust-toolchain@1.88
+      - uses: dtolnay/rust-toolchain@1.89
         with:
           targets: x86_64-unknown-linux-gnu
           components: clippy
@@ -52,7 +52,7 @@ jobs:
             ~/.cargo/registry/cache/
             ~/.cargo/git/db/
             ${{ github.workspace }}/codex-rs/target/
-          key: cargo-ubuntu-24.04-x86_64-unknown-linux-gnu-${{ hashFiles('**/Cargo.lock') }}
+          key: cargo-ubuntu-24.04-x86_64-unknown-linux-gnu-dev-${{ hashFiles('**/Cargo.lock') }}
 
       # Note it is possible that the `verify` step internal to Run Codex will
       # fail, in which case the work to setup the repo was worthless :(

.github/workflows/rust-ci.yml

@@ -17,7 +17,7 @@ jobs:
       codex: ${{ steps.detect.outputs.codex }}
       workflows: ${{ steps.detect.outputs.workflows }}
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
         with:
           fetch-depth: 0
       - name: Detect changed paths (no external action)
@@ -56,8 +56,8 @@ jobs:
       run:
         working-directory: codex-rs
     steps:
-      - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@1.88
+      - uses: actions/checkout@v5
+      - uses: dtolnay/rust-toolchain@1.89
         with:
           components: rustfmt
       - name: cargo fmt
@@ -111,8 +111,8 @@ jobs:
             profile: release
 
     steps:
-      - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@1.88
+      - uses: actions/checkout@v5
+      - uses: dtolnay/rust-toolchain@1.89
         with:
           targets: ${{ matrix.target }}
           components: clippy
@@ -130,7 +130,7 @@ jobs:
       - if: ${{ matrix.target == 'x86_64-unknown-linux-musl' || matrix.target == 'aarch64-unknown-linux-musl'}}
         name: Install musl build tools
         run: |
-          sudo apt install -y musl-tools pkg-config
+          sudo apt install -y musl-tools pkg-config && sudo rm -rf /var/lib/apt/lists/*
 
       - name: cargo clippy
         id: clippy
@@ -139,15 +139,15 @@ jobs:
       # Running `cargo build` from the workspace root builds the workspace using
       # the union of all features from third-party crates. This can mask errors
       # where individual crates have underspecified features. To avoid this, we
-      # run `cargo build` for each crate individually, though because this is
+      # run `cargo check` for each crate individually, though because this is
       # slower, we only do this for the x86_64-unknown-linux-gnu target.
-      - name: cargo build individual crates
-        id: build
+      - name: cargo check individual crates
+        id: cargo_check_all_crates
         if: ${{ matrix.target == 'x86_64-unknown-linux-gnu' && matrix.profile != 'release' }}
         continue-on-error: true
         run: |
           find . -name Cargo.toml -mindepth 2 -maxdepth 2 -print0 \
-            | xargs -0 -n1 -I{} bash -c 'cd "$(dirname "{}")" && cargo build --profile ${{ matrix.profile }}'
+            | xargs -0 -n1 -I{} bash -c 'cd "$(dirname "{}")" && cargo check --profile ${{ matrix.profile }}'
 
       - name: cargo test
         id: test
@@ -162,10 +162,10 @@ jobs:
       - name: verify all steps passed
         if: |
           steps.clippy.outcome == 'failure' ||
-          steps.build.outcome == 'failure' ||
+          steps.cargo_check_all_crates.outcome == 'failure' ||
           steps.test.outcome == 'failure'
         run: |
-          echo "One or more checks failed (clippy, build, or test). See logs for details."
+          echo "One or more checks failed (clippy, cargo_check_all_crates, or test). See logs for details."
           exit 1
 
   # --- Gatherer job that you mark as the ONLY required status -----------------

.github/workflows/rust-release.yml

@@ -19,7 +19,7 @@ jobs:
   tag-check:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
 
       - name: Validate tag matches Cargo.toml version
         shell: bash
@@ -74,8 +74,8 @@ jobs:
             target: x86_64-pc-windows-msvc
 
     steps:
-      - uses: actions/checkout@v4
-      - uses: dtolnay/rust-toolchain@1.88
+      - uses: actions/checkout@v5
+      - uses: dtolnay/rust-toolchain@1.89
         with:
           targets: ${{ matrix.target }}
 
@@ -95,7 +95,7 @@ jobs:
           sudo apt install -y musl-tools pkg-config
 
       - name: Cargo build
-        run: cargo build --target ${{ matrix.target }} --release --bin codex
+        run: cargo build --target ${{ matrix.target }} --release --bin codex --bin apply-patch
 
       - name: Stage artifacts
         shell: bash
@@ -105,8 +105,10 @@ jobs:
 
           if [[ "${{ matrix.runner }}" == windows* ]]; then
             cp target/${{ matrix.target }}/release/codex.exe "$dest/codex-${{ matrix.target }}.exe"
+            cp target/${{ matrix.target }}/release/apply-patch.exe "$dest/apply-patch-${{ matrix.target }}.exe"
           else
             cp target/${{ matrix.target }}/release/codex "$dest/codex-${{ matrix.target }}"
+            cp target/${{ matrix.target }}/release/apply-patch "$dest/apply-patch-${{ matrix.target }}"
           fi
 
       - name: Compress artifacts
@@ -117,10 +119,11 @@ jobs:
           dest="dist/${{ matrix.target }}"
 
           # For compatibility with environments that lack the `zstd` tool we
-          # additionally create a `.tar.gz` alongside every single binary that
-          # we publish. The end result is:
+          # additionally create a `.tar.gz` for all platforms and `.zip` for
+          # Windows alongside every single binary that we publish. The end result is:
           #   codex-<target>.zst          (existing)
           #   codex-<target>.tar.gz       (new)
+          #   codex-<target>.zip          (only for Windows)
 
           # 1. Produce a .tar.gz for every file in the directory *before* we
           #    run `zstd --rm`, because that flag deletes the original files.
@@ -128,13 +131,20 @@ jobs:
             base="$(basename "$f")"
             # Skip files that are already archives (shouldn't happen, but be
             # safe).
-            if [[ "$base" == *.tar.gz ]]; then
+            if [[ "$base" == *.tar.gz || "$base" == *.zip ]]; then
               continue
             fi
 
             # Create per-binary tar.gz
             tar -C "$dest" -czf "$dest/${base}.tar.gz" "$base"
 
+            # Create zip archive for Windows binaries
+            # Must run from inside the dest dir so 7z won't
+            # embed the directory path inside the zip.
+            if [[ "${{ matrix.runner }}" == windows* ]]; then
+              (cd "$dest" && 7z a "${base}.zip" "$base")
+            fi
+
             # Also create .zst (existing behaviour) *and* remove the original
             # uncompressed binary to keep the directory small.
             zstd -T0 -19 --rm "$dest/$base"
@@ -155,7 +165,7 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - uses: actions/download-artifact@v4
         with:

.prettierignore

@@ -1,3 +1,7 @@
 /codex-cli/dist
 /codex-cli/node_modules
 pnpm-lock.yaml
+
+prompt.md
+*_prompt.md
+*_instructions.md

.vscode/launch.json

@@ -1,18 +1,22 @@
 {
-    "version": "0.2.0",
-    "configurations": [
-        {
-            "type": "lldb",
-            "request": "launch",
-            "name": "Cargo launch",
-            "cargo": {
-                "cwd": "${workspaceFolder}/codex-rs",
-                "args": [
-                    "build",
-                    "--bin=codex-tui"
-                ]
-            },
-            "args": []
-        }
-    ]
+  "version": "0.2.0",
+  "configurations": [
+    {
+      "type": "lldb",
+      "request": "launch",
+      "name": "Cargo launch",
+      "cargo": {
+        "cwd": "${workspaceFolder}/codex-rs",
+        "args": ["build", "--bin=codex-tui"]
+      },
+      "args": []
+    },
+    {
+      "type": "lldb",
+      "request": "attach",
+      "name": "Attach to running codex CLI",
+      "pid": "${command:pickProcess}",
+      "sourceLanguages": ["rust"]
+    }
+  ]
 }

AGENTS.md

@@ -2,12 +2,41 @@
 
 In the codex-rs folder where the rust code lives:
 
-- Crate names are prefixed with `codex-`. For examole, the `core` folder's crate is named `codex-core`
+- Crate names are prefixed with `codex-`. For example, the `core` folder's crate is named `codex-core`
 - When using format! and you can inline variables into {}, always do that.
 - Never add or modify any code related to `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` or `CODEX_SANDBOX_ENV_VAR`.
   - You operate in a sandbox where `CODEX_SANDBOX_NETWORK_DISABLED=1` will be set whenever you use the `shell` tool. Any existing code that uses `CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR` was authored with this fact in mind. It is often used to early exit out of tests that the author knew you would not be able to run given your sandbox limitations.
   - Similarly, when you spawn a process using Seatbelt (`/usr/bin/sandbox-exec`), `CODEX_SANDBOX=seatbelt` will be set on the child process. Integration tests that want to run Seatbelt themselves cannot be run under Seatbelt, so checks for `CODEX_SANDBOX=seatbelt` are also often used to early exit out of tests, as appropriate.
 
-Before finalizing a change to `codex-rs`, run `just fmt` (in `codex-rs` directory) to format the code and `just fix` (in `codex-rs` directory) to fix any linter issues in the code. Additionally, run the tests:
+Before finalizing a change to `codex-rs`, run `just fmt` (in `codex-rs` directory) to format the code and `just fix -p <project>` (in `codex-rs` directory) to fix any linter issues in the code. Additionally, run the tests:
 1. Run the test for the specific project that was changed. For example, if changes were made in `codex-rs/tui`, run `cargo test -p codex-tui`.
 2. Once those pass, if any changes were made in common, core, or protocol, run the complete test suite with `cargo test --all-features`.
+
+## TUI style conventions
+
+See `codex-rs/tui/styles.md`.
+
+## TUI code conventions
+
+- Use concise styling helpers from ratatui’s Stylize trait.
+  - Basic spans: use "text".into()
+  - Styled spans: use "text".red(), "text".green(), "text".magenta(), "text".dim(), etc.
+  - Prefer these over constructing styles with `Span::styled` and `Style` directly.
+  - Example: patch summary file lines
+    - Desired: vec!["  └ ".into(), "M".red(), " ".dim(), "tui/src/app.rs".dim()]
+
+## Snapshot tests
+
+This repo uses snapshot tests (via `insta`), especially in `codex-rs/tui`, to validate rendered output. When UI or text output changes intentionally, update the snapshots as follows:
+
+- Run tests to generate any updated snapshots:
+  - `cargo test -p codex-tui`
+- Check what’s pending:
+  - `cargo insta pending-snapshots -p codex-tui`
+- Review changes by reading the generated `*.snap.new` files directly in the repo, or preview a specific file:
+  - `cargo insta show -p codex-tui path/to/file.snap.new`
+- Only if you intend to accept all new snapshots in this crate, run:
+  - `cargo insta accept -p codex-tui`
+
+If you don’t have the tool:
+- `cargo install cargo-insta`

README.md

@@ -22,6 +22,7 @@
     - [Authenticate locally and copy your credentials to the "headless" machine](#authenticate-locally-and-copy-your-credentials-to-the-headless-machine)
     - [Connecting through VPS or remote](#connecting-through-vps-or-remote)
   - [Usage-based billing alternative: Use an OpenAI API key](#usage-based-billing-alternative-use-an-openai-api-key)
+    - [Forcing a specific auth method (advanced)](#forcing-a-specific-auth-method-advanced)
   - [Choosing Codex's level of autonomy](#choosing-codexs-level-of-autonomy)
     - [**1. Read/write**](#1-readwrite)
     - [**2. Read-only**](#2-read-only)
@@ -165,6 +166,35 @@ Notes:
 - This command only sets the key for your current terminal session, which we recommend. To set it for all future sessions, you can also add the `export` line to your shell's configuration file (e.g., `~/.zshrc`).
 - If you have signed in with ChatGPT, Codex will default to using your ChatGPT credits. If you wish to use your API key, use the `/logout` command to clear your ChatGPT authentication.
 
+#### Forcing a specific auth method (advanced)
+
+You can explicitly choose which authentication Codex should prefer when both are available.
+
+- To always use your API key (even when ChatGPT auth exists), set:
+
+```toml
+# ~/.codex/config.toml
+preferred_auth_method = "apikey"
+```
+
+Or override ad-hoc via CLI:
+
+```bash
+codex --config preferred_auth_method="apikey"
+```
+
+- To prefer ChatGPT auth (default), set:
+
+```toml
+# ~/.codex/config.toml
+preferred_auth_method = "chatgpt"
+```
+
+Notes:
+
+- When `preferred_auth_method = "apikey"` and an API key is available, the login screen is skipped.
+- When `preferred_auth_method = "chatgpt"` (default), Codex prefers ChatGPT auth if present; if only an API key is present, it will use the API key. Certain account types may also require API-key mode.
+
 ### Choosing Codex's level of autonomy
 
 We always recommend running Codex in its default sandbox that gives you strong guardrails around what the agent can do. The default sandbox prevents it from editing files outside its workspace, or from accessing the network.
@@ -353,6 +383,13 @@ base_url = "http://my-ollama.example.com:11434/v1"
 
 ### Platform sandboxing details
 
+By default, Codex CLI runs code and shell commands inside a restricted sandbox to protect your system.  
+
+> [!IMPORTANT]
+> Not all tool calls are sandboxed. Specifically, **trusted Model Context Protocol (MCP) tool calls** are executed outside of the sandbox.  
+> This is intentional: MCP tools are explicitly configured and trusted by you, and they often need to connect to **external applications or services** (e.g. issue trackers, databases, messaging systems).  
+> Running them outside the sandbox allows Codex to integrate with these external systems without being blocked by sandbox restrictions.
+
 The mechanism Codex uses to implement the sandbox policy depends on your OS:
 
 - **macOS 12+** uses **Apple Seatbelt** and runs commands using `sandbox-exec` with a profile (`-p`) that corresponds to the `--sandbox` that was specified.

codex-cli/bin/codex.js

@@ -2,6 +2,9 @@
 // Unified entry point for the Codex CLI.
 
 import path from "path";
+import os from "os";
+import fs from "fs";
+import { createRequire } from "module";
 import { fileURLToPath } from "url";
 
 // __dirname equivalent in ESM
@@ -56,7 +59,9 @@ if (!targetTriple) {
   throw new Error(`Unsupported platform: ${platform} (${arch})`);
 }
 
-const binaryPath = path.join(__dirname, "..", "bin", `codex-${targetTriple}`);
+const pkgRoot = path.join(__dirname, "..");
+const pkgBinDir = path.join(pkgRoot, "bin");
+const binaryPath = path.join(pkgBinDir, `codex-${targetTriple}`);
 
 // Use an asynchronous spawn instead of spawnSync so that Node is able to
 // respond to signals (e.g. Ctrl-C / SIGINT) while the native binary is
@@ -93,10 +98,35 @@ function getUpdatedPath(newDirs) {
 }
 
 const additionalDirs = [];
+// 1) Make packaged bin directory available on PATH for any helper binaries.
+additionalDirs.push(pkgBinDir);
 const rgDir = await resolveRgDir();
 if (rgDir) {
   additionalDirs.push(rgDir);
 }
+// 2) Ensure an `apply_patch` helper exists in $CODEX_HOME/<version>/ and add that directory to PATH.
+try {
+  const require = createRequire(import.meta.url);
+  // Load package.json to read the version string.
+  const { version } = require("../package.json");
+  const codexHome = process.env.CODEX_HOME || path.join(os.homedir(), ".codex");
+  const versionDir = path.join(codexHome, version);
+  fs.mkdirSync(versionDir, { recursive: true });
+  const isWindows = platform === "win32";
+  const destName = isWindows ? "apply_patch.exe" : "apply_patch";
+  const destPath = path.join(versionDir, destName);
+  const srcPath = path.join(pkgBinDir, `apply-patch-${targetTriple}`);
+  // Only copy if missing; keep it simple and fast.
+  if (!fs.existsSync(destPath)) {
+    fs.copyFileSync(srcPath, destPath);
+    if (!isWindows) {
+      fs.chmodSync(destPath, 0o755);
+    }
+  }
+  additionalDirs.push(versionDir);
+} catch {
+  // Best-effort: if anything fails, continue without the helper.
+}
 const updatedPath = getUpdatedPath(additionalDirs);
 
 const child = spawn(binaryPath, process.argv.slice(2), {

codex-cli/scripts/install_native_deps.sh

@@ -75,17 +75,32 @@ gh run download --dir "$ARTIFACTS_DIR" --repo openai/codex "$WORKFLOW_ID"
 # x64 Linux
 zstd -d "$ARTIFACTS_DIR/x86_64-unknown-linux-musl/codex-x86_64-unknown-linux-musl.zst" \
     -o "$BIN_DIR/codex-x86_64-unknown-linux-musl"
+if [ -f "$ARTIFACTS_DIR/x86_64-unknown-linux-musl/apply-patch-x86_64-unknown-linux-musl.zst" ]; then
+  zstd -d "$ARTIFACTS_DIR/x86_64-unknown-linux-musl/apply-patch-x86_64-unknown-linux-musl.zst" -o "$BIN_DIR/apply-patch-x86_64-unknown-linux-musl"
+fi
 # ARM64 Linux
 zstd -d "$ARTIFACTS_DIR/aarch64-unknown-linux-musl/codex-aarch64-unknown-linux-musl.zst" \
     -o "$BIN_DIR/codex-aarch64-unknown-linux-musl"
+if [ -f "$ARTIFACTS_DIR/aarch64-unknown-linux-musl/apply-patch-aarch64-unknown-linux-musl.zst" ]; then
+  zstd -d "$ARTIFACTS_DIR/aarch64-unknown-linux-musl/apply-patch-aarch64-unknown-linux-musl.zst" -o "$BIN_DIR/apply-patch-aarch64-unknown-linux-musl"
+fi
 # x64 macOS
 zstd -d "$ARTIFACTS_DIR/x86_64-apple-darwin/codex-x86_64-apple-darwin.zst" \
     -o "$BIN_DIR/codex-x86_64-apple-darwin"
+if [ -f "$ARTIFACTS_DIR/x86_64-apple-darwin/apply-patch-x86_64-apple-darwin.zst" ]; then
+  zstd -d "$ARTIFACTS_DIR/x86_64-apple-darwin/apply-patch-x86_64-apple-darwin.zst" -o "$BIN_DIR/apply-patch-x86_64-apple-darwin"
+fi
 # ARM64 macOS
 zstd -d "$ARTIFACTS_DIR/aarch64-apple-darwin/codex-aarch64-apple-darwin.zst" \
     -o "$BIN_DIR/codex-aarch64-apple-darwin"
+if [ -f "$ARTIFACTS_DIR/aarch64-apple-darwin/apply-patch-aarch64-apple-darwin.zst" ]; then
+  zstd -d "$ARTIFACTS_DIR/aarch64-apple-darwin/apply-patch-aarch64-apple-darwin.zst" -o "$BIN_DIR/apply-patch-aarch64-apple-darwin"
+fi
 # x64 Windows
 zstd -d "$ARTIFACTS_DIR/x86_64-pc-windows-msvc/codex-x86_64-pc-windows-msvc.exe.zst" \
     -o "$BIN_DIR/codex-x86_64-pc-windows-msvc.exe"
+if [ -f "$ARTIFACTS_DIR/x86_64-pc-windows-msvc/apply-patch-x86_64-pc-windows-msvc.exe.zst" ]; then
+  zstd -d "$ARTIFACTS_DIR/x86_64-pc-windows-msvc/apply-patch-x86_64-pc-windows-msvc.exe.zst" -o "$BIN_DIR/apply-patch-x86_64-pc-windows-msvc.exe"
+fi
 
 echo "Installed native dependencies into $BIN_DIR"

codex-rs/Cargo.lock

@@ -176,9 +176,9 @@ dependencies = [
 
 [[package]]
 name = "anyhow"
-version = "1.0.98"
+version = "1.0.99"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "e16d2d3311acee920a9eb8d33b8cbc1787ce4a264e85f964c2404b969bdcd487"
+checksum = "b0674a1ddeecb70197781e945de4b3b8ffb61fa939a5597bcf48503737663100"
 
 [[package]]
 name = "arbitrary"
@@ -186,6 +186,26 @@ version = "1.4.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "dde20b3d026af13f561bdd0f15edf01fc734f0dafcedbaf42bba506a9517f223"
 
+[[package]]
+name = "arboard"
+version = "3.6.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "55f533f8e0af236ffe5eb979b99381df3258853f00ba2e44b6e1955292c75227"
+dependencies = [
+ "clipboard-win",
+ "image",
+ "log",
+ "objc2",
+ "objc2-app-kit",
+ "objc2-core-foundation",
+ "objc2-core-graphics",
+ "objc2-foundation",
+ "parking_lot",
+ "percent-encoding",
+ "windows-sys 0.59.0",
+ "x11rb",
+]
+
 [[package]]
 name = "arg_enum_proc_macro"
 version = "0.3.4"
@@ -538,9 +558,9 @@ checksum = "6e4de3bc4ea267985becf712dc6d9eed8b04c953b3fcfb339ebc87acd9804901"
 
 [[package]]
 name = "clap"
-version = "4.5.43"
+version = "4.5.45"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "50fd97c9dc2399518aa331917ac6f274280ec5eb34e555dd291899745c48ec6f"
+checksum = "1fc0e74a703892159f5ae7d3aac52c8e6c392f5ae5f359c70b5881d60aaac318"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -548,9 +568,9 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.5.43"
+version = "4.5.44"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "c35b5830294e1fa0462034af85cc95225a4cb07092c088c55bda3147cfcd8f65"
+checksum = "b3e7f4214277f3c7aa526a59dd3fbe306a370daee1f8b7b8c987069cd8e888a8"
 dependencies = [
  "anstream",
  "anstyle",
@@ -561,18 +581,18 @@ dependencies = [
 
 [[package]]
 name = "clap_complete"
-version = "4.5.56"
+version = "4.5.57"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "67e4efcbb5da11a92e8a609233aa1e8a7d91e38de0be865f016d14700d45a7fd"
+checksum = "4d9501bd3f5f09f7bbee01da9a511073ed30a80cd7a509f1214bb74eadea71ad"
 dependencies = [
  "clap",
 ]
 
 [[package]]
 name = "clap_derive"
-version = "4.5.41"
+version = "4.5.45"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ef4f52386a59ca4c860f7393bcf8abd8dfd91ecccc0f774635ff68e92eeef491"
+checksum = "14cb31bb0a7d536caef2639baa7fad459e15c3144efefa6dbd1c84562c4739f6"
 dependencies = [
  "heck",
  "proc-macro2",
@@ -615,6 +635,7 @@ name = "codex-apply-patch"
 version = "0.0.0"
 dependencies = [
  "anyhow",
+ "assert_cmd",
  "pretty_assertions",
  "similar",
  "tempfile",
@@ -665,6 +686,8 @@ dependencies = [
  "codex-exec",
  "codex-login",
  "codex-mcp-server",
+ "codex-protocol",
+ "codex-protocol-ts",
  "codex-tui",
  "serde_json",
  "tokio",
@@ -678,6 +701,7 @@ version = "0.0.0"
 dependencies = [
  "clap",
  "codex-core",
+ "codex-protocol",
  "serde",
  "toml 0.9.5",
 ]
@@ -695,11 +719,11 @@ dependencies = [
  "codex-apply-patch",
  "codex-login",
  "codex-mcp-client",
+ "codex-protocol",
  "core_test_support",
  "dirs",
  "env-flags",
  "eventsource-stream",
- "fs2",
  "futures",
  "landlock",
  "libc",
@@ -708,6 +732,7 @@ dependencies = [
  "mime_guess",
  "openssl-sys",
  "os_info",
+ "portable-pty",
  "predicates",
  "pretty_assertions",
  "rand 0.9.2",
@@ -734,6 +759,7 @@ dependencies = [
  "tree-sitter-bash",
  "uuid",
  "walkdir",
+ "which",
  "whoami",
  "wildmatch",
  "wiremock",
@@ -750,7 +776,10 @@ dependencies = [
  "codex-arg0",
  "codex-common",
  "codex-core",
+ "codex-login",
  "codex-ollama",
+ "codex-protocol",
+ "core_test_support",
  "libc",
  "owo-colors",
  "predicates",
@@ -760,6 +789,7 @@ dependencies = [
  "tokio",
  "tracing",
  "tracing-subscriber",
+ "wiremock",
 ]
 
 [[package]]
@@ -816,6 +846,7 @@ version = "0.0.0"
 dependencies = [
  "base64 0.22.1",
  "chrono",
+ "codex-protocol",
  "pretty_assertions",
  "rand 0.8.5",
  "reqwest",
@@ -851,7 +882,10 @@ dependencies = [
  "anyhow",
  "assert_cmd",
  "codex-arg0",
+ "codex-common",
  "codex-core",
+ "codex-login",
+ "codex-protocol",
  "mcp-types",
  "mcp_test_support",
  "pretty_assertions",
@@ -887,11 +921,41 @@ dependencies = [
  "wiremock",
 ]
 
+[[package]]
+name = "codex-protocol"
+version = "0.0.0"
+dependencies = [
+ "base64 0.22.1",
+ "mcp-types",
+ "mime_guess",
+ "pretty_assertions",
+ "serde",
+ "serde_bytes",
+ "serde_json",
+ "strum 0.27.2",
+ "strum_macros 0.27.2",
+ "tracing",
+ "ts-rs",
+ "uuid",
+]
+
+[[package]]
+name = "codex-protocol-ts"
+version = "0.0.0"
+dependencies = [
+ "anyhow",
+ "clap",
+ "codex-protocol",
+ "ts-rs",
+]
+
 [[package]]
 name = "codex-tui"
 version = "0.0.0"
 dependencies = [
  "anyhow",
+ "arboard",
+ "async-stream",
  "base64 0.22.1",
  "chrono",
  "clap",
@@ -902,6 +966,7 @@ dependencies = [
  "codex-file-search",
  "codex-login",
  "codex-ollama",
+ "codex-protocol",
  "color-eyre",
  "crossterm",
  "diffy",
@@ -913,7 +978,7 @@ dependencies = [
  "once_cell",
  "path-clean",
  "pretty_assertions",
- "rand 0.8.5",
+ "rand 0.9.2",
  "ratatui",
  "ratatui-image",
  "regex-lite",
@@ -924,8 +989,10 @@ dependencies = [
  "strum 0.27.2",
  "strum_macros 0.27.2",
  "supports-color",
+ "tempfile",
  "textwrap 0.16.2",
  "tokio",
+ "tokio-stream",
  "tracing",
  "tracing-appender",
  "tracing-subscriber",
@@ -1126,6 +1193,7 @@ checksum = "829d955a0bb380ef178a640b91779e3987da38c9aea133b20614cfed8cdea9c6"
 dependencies = [
  "bitflags 2.9.1",
  "crossterm_winapi",
+ "futures-core",
  "mio",
  "parking_lot",
  "rustix 0.38.44",
@@ -1370,6 +1438,16 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "dispatch2"
+version = "0.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "89a09f22a6c6069a18470eb92d2298acf25463f14256d24778e1230d789a2aec"
+dependencies = [
+ "bitflags 2.9.1",
+ "objc2",
+]
+
 [[package]]
 name = "display_container"
 version = "0.9.0"
@@ -1403,6 +1481,12 @@ version = "0.15.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "1aaf95b3e5c8f23aa320147307562d361db0ae0d51242340f558153b4eb2439b"
 
+[[package]]
+name = "downcast-rs"
+version = "1.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "75b325c5dbd37f80359721ad39aca5a29fb04c89279657cffdda8736d0c0b9d2"
+
 [[package]]
 name = "dupe"
 version = "0.9.1"
@@ -1648,6 +1732,17 @@ dependencies = [
  "simd-adler32",
 ]
 
+[[package]]
+name = "filedescriptor"
+version = "0.8.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e40758ed24c9b2eeb76c35fb0aebc66c626084edd827e07e1552279814c6682d"
+dependencies = [
+ "libc",
+ "thiserror 1.0.69",
+ "winapi",
+]
+
 [[package]]
 name = "fixedbitset"
 version = "0.4.2"
@@ -1709,16 +1804,6 @@ dependencies = [
  "percent-encoding",
 ]
 
-[[package]]
-name = "fs2"
-version = "0.4.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "9564fc758e15025b46aa6643b1b77d047d1a56a1aea6e01002ac0c7026876213"
-dependencies = [
- "libc",
- "winapi",
-]
-
 [[package]]
 name = "futures"
 version = "0.3.31"
@@ -1833,6 +1918,16 @@ dependencies = [
  "version_check",
 ]
 
+[[package]]
+name = "gethostname"
+version = "0.4.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0176e0459c2e4a1fe232f984bca6890e681076abb9934f6cea7c326f3fc47818"
+dependencies = [
+ "libc",
+ "windows-targets 0.48.5",
+]
+
 [[package]]
 name = "getopts"
 version = "0.2.23"
@@ -2604,9 +2699,9 @@ checksum = "03087c2bad5e1034e8cace5926dec053fb3790248370865f5117a7d0213354c8"
 
 [[package]]
 name = "libc"
-version = "0.2.174"
+version = "0.2.175"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "1171693293099992e19cddea4e8b849964e9846f4acee11b3948bcc337be8776"
+checksum = "6a82ae493e598baaea5209805c49bbf2ea7de956d50d7da0da1164f9c6d28543"
 
 [[package]]
 name = "libfuzzer-sys"
@@ -2753,6 +2848,7 @@ version = "0.0.0"
 dependencies = [
  "serde",
  "serde_json",
+ "ts-rs",
 ]
 
 [[package]]
@@ -2763,8 +2859,10 @@ dependencies = [
  "assert_cmd",
  "codex-core",
  "codex-mcp-server",
+ "codex-protocol",
  "mcp-types",
  "pretty_assertions",
+ "serde",
  "serde_json",
  "shlex",
  "tempfile",
@@ -3026,6 +3124,42 @@ dependencies = [
  "objc2-encode",
 ]
 
+[[package]]
+name = "objc2-app-kit"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e6f29f568bec459b0ddff777cec4fe3fd8666d82d5a40ebd0ff7e66134f89bcc"
+dependencies = [
+ "bitflags 2.9.1",
+ "objc2",
+ "objc2-core-graphics",
+ "objc2-foundation",
+]
+
+[[package]]
+name = "objc2-core-foundation"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1c10c2894a6fed806ade6027bcd50662746363a9589d3ec9d9bef30a4e4bc166"
+dependencies = [
+ "bitflags 2.9.1",
+ "dispatch2",
+ "objc2",
+]
+
+[[package]]
+name = "objc2-core-graphics"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "989c6c68c13021b5c2d6b71456ebb0f9dc78d752e86a98da7c716f4f9470f5a4"
+dependencies = [
+ "bitflags 2.9.1",
+ "dispatch2",
+ "objc2",
+ "objc2-core-foundation",
+ "objc2-io-surface",
+]
+
 [[package]]
 name = "objc2-encode"
 version = "4.1.0"
@@ -3040,6 +3174,18 @@ checksum = "900831247d2fe1a09a683278e5384cfb8c80c79fe6b166f9d14bfdde0ea1b03c"
 dependencies = [
  "bitflags 2.9.1",
  "objc2",
+ "objc2-core-foundation",
+]
+
+[[package]]
+name = "objc2-io-surface"
+version = "0.3.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "7282e9ac92529fa3457ce90ebb15f4ecbc383e8338060960760fa2cf75420c3c"
+dependencies = [
+ "bitflags 2.9.1",
+ "objc2",
+ "objc2-core-foundation",
 ]
 
 [[package]]
@@ -3312,6 +3458,27 @@ dependencies = [
  "portable-atomic",
 ]
 
+[[package]]
+name = "portable-pty"
+version = "0.9.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4a596a2b3d2752d94f51fac2d4a96737b8705dddd311a32b9af47211f08671e"
+dependencies = [
+ "anyhow",
+ "bitflags 1.3.2",
+ "downcast-rs",
+ "filedescriptor",
+ "lazy_static",
+ "libc",
+ "log",
+ "nix",
+ "serial2",
+ "shared_library",
+ "shell-words",
+ "winapi",
+ "winreg",
+]
+
 [[package]]
 name = "potential_utf"
 version = "0.1.2"
@@ -3761,9 +3928,9 @@ checksum = "ba39f3699c378cd8970968dcbff9c43159ea4cfbd88d43c00b22f2ef10a435d2"
 
 [[package]]
 name = "reqwest"
-version = "0.12.22"
+version = "0.12.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "cbc931937e6ca3a06e3b6c0aa7841849b160a90351d6ab467a8b9b9959767531"
+checksum = "d429f34c8092b2d42c7c93cec323bb4adeb7c67698f70839adec842ec10c7ceb"
 dependencies = [
  "base64 0.22.1",
  "bytes",
@@ -4155,9 +4322,9 @@ dependencies = [
 
 [[package]]
 name = "serde_json"
-version = "1.0.142"
+version = "1.0.143"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "030fedb782600dcbd6f02d479bf0d817ac3bb40d644745b769d6a96bc3afc5a7"
+checksum = "d401abef1d108fbd9cbaebc3e46611f4b1021f714a0597a71f41ee463f5f4a5a"
 dependencies = [
  "indexmap 2.10.0",
  "itoa",
@@ -4239,6 +4406,17 @@ dependencies = [
  "syn 2.0.104",
 ]
 
+[[package]]
+name = "serial2"
+version = "0.2.31"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "26e1e5956803a69ddd72ce2de337b577898801528749565def03515f82bad5bb"
+dependencies = [
+ "cfg-if",
+ "libc",
+ "winapi",
+]
+
 [[package]]
 name = "sha1"
 version = "0.10.6"
@@ -4270,6 +4448,22 @@ dependencies = [
  "lazy_static",
 ]
 
+[[package]]
+name = "shared_library"
+version = "0.1.9"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5a9e7e0f2bfae24d8a5b5a66c5b257a83c7412304311512a0c054cd5e619da11"
+dependencies = [
+ "lazy_static",
+ "libc",
+]
+
+[[package]]
+name = "shell-words"
+version = "1.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "24188a676b6ae68c3b2cb3a01be17fbf7240ce009799bb56d5b1409051e78fde"
+
 [[package]]
 name = "shlex"
 version = "1.3.0"
@@ -4682,6 +4876,15 @@ dependencies = [
  "winapi",
 ]
 
+[[package]]
+name = "termcolor"
+version = "1.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "06794f8f6c5c898b3275aebefa6b8a1cb24cd2c6c79397ab15774837a0bc5755"
+dependencies = [
+ "winapi-util",
+]
+
 [[package]]
 name = "terminal_size"
 version = "0.4.2"
@@ -5181,6 +5384,30 @@ version = "0.2.5"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e421abadd41a4225275504ea4d6566923418b7f05506fbc9c0fe86ba7396114b"
 
+[[package]]
+name = "ts-rs"
+version = "11.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6ef1b7a6d914a34127ed8e1fa927eb7088903787bcded4fa3eef8f85ee1568be"
+dependencies = [
+ "serde_json",
+ "thiserror 2.0.12",
+ "ts-rs-macros",
+ "uuid",
+]
+
+[[package]]
+name = "ts-rs-macros"
+version = "11.0.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "e9d4ed7b4c18cc150a6a0a1e9ea1ecfa688791220781af6e119f9599a8502a0a"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn 2.0.104",
+ "termcolor",
+]
+
 [[package]]
 name = "tui-input"
 version = "0.14.0"
@@ -5535,6 +5762,18 @@ version = "0.1.10"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a751b3277700db47d3e574514de2eced5e54dc8a5436a3bf7a0b248b2cee16f3"
 
+[[package]]
+name = "which"
+version = "6.0.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b4ee928febd44d98f2f459a4a79bd4d928591333a494a10a868418ac1b39cf1f"
+dependencies = [
+ "either",
+ "home",
+ "rustix 0.38.44",
+ "winsafe",
+]
+
 [[package]]
 name = "whoami"
 version = "1.6.0"
@@ -5768,6 +6007,21 @@ dependencies = [
  "windows_x86_64_msvc 0.42.2",
 ]
 
+[[package]]
+name = "windows-targets"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9a2fa6e2155d7247be68c096456083145c183cbbbc2764150dda45a87197940c"
+dependencies = [
+ "windows_aarch64_gnullvm 0.48.5",
+ "windows_aarch64_msvc 0.48.5",
+ "windows_i686_gnu 0.48.5",
+ "windows_i686_msvc 0.48.5",
+ "windows_x86_64_gnu 0.48.5",
+ "windows_x86_64_gnullvm 0.48.5",
+ "windows_x86_64_msvc 0.48.5",
+]
+
 [[package]]
 name = "windows-targets"
 version = "0.52.6"
@@ -5806,6 +6060,12 @@ version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "597a5118570b68bc08d8d59125332c54f1ba9d9adeedeef5b99b02ba2b0698f8"
 
+[[package]]
+name = "windows_aarch64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2b38e32f0abccf9987a4e3079dfb67dcd799fb61361e53e2882c3cbaf0d905d8"
+
 [[package]]
 name = "windows_aarch64_gnullvm"
 version = "0.52.6"
@@ -5824,6 +6084,12 @@ version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "e08e8864a60f06ef0d0ff4ba04124db8b0fb3be5776a5cd47641e942e58c4d43"
 
+[[package]]
+name = "windows_aarch64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "dc35310971f3b2dbbf3f0690a219f40e2d9afcf64f9ab7cc1be722937c26b4bc"
+
 [[package]]
 name = "windows_aarch64_msvc"
 version = "0.52.6"
@@ -5842,6 +6108,12 @@ version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "c61d927d8da41da96a81f029489353e68739737d3beca43145c8afec9a31a84f"
 
+[[package]]
+name = "windows_i686_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a75915e7def60c94dcef72200b9a8e58e5091744960da64ec734a6c6e9b3743e"
+
 [[package]]
 name = "windows_i686_gnu"
 version = "0.52.6"
@@ -5872,6 +6144,12 @@ version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "44d840b6ec649f480a41c8d80f9c65108b92d89345dd94027bfe06ac444d1060"
 
+[[package]]
+name = "windows_i686_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8f55c233f70c4b27f66c523580f78f1004e8b5a8b659e05a4eb49d4166cca406"
+
 [[package]]
 name = "windows_i686_msvc"
 version = "0.52.6"
@@ -5890,6 +6168,12 @@ version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "8de912b8b8feb55c064867cf047dda097f92d51efad5b491dfb98f6bbb70cb36"
 
+[[package]]
+name = "windows_x86_64_gnu"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "53d40abd2583d23e4718fddf1ebec84dbff8381c07cae67ff7768bbf19c6718e"
+
 [[package]]
 name = "windows_x86_64_gnu"
 version = "0.52.6"
@@ -5908,6 +6192,12 @@ version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "26d41b46a36d453748aedef1486d5c7a85db22e56aff34643984ea85514e94a3"
 
+[[package]]
+name = "windows_x86_64_gnullvm"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0b7b52767868a23d5bab768e390dc5f5c55825b6d30b86c844ff2dc7414044cc"
+
 [[package]]
 name = "windows_x86_64_gnullvm"
 version = "0.52.6"
@@ -5926,6 +6216,12 @@ version = "0.42.2"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9aec5da331524158c6d1a4ac0ab1541149c0b9505fde06423b02f5ef0106b9f0"
 
+[[package]]
+name = "windows_x86_64_msvc"
+version = "0.48.5"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ed94fce61571a4006852b7389a063ab983c02eb1bb37b47f8272ce92d06d9538"
+
 [[package]]
 name = "windows_x86_64_msvc"
 version = "0.52.6"
@@ -5947,6 +6243,21 @@ dependencies = [
  "memchr",
 ]
 
+[[package]]
+name = "winreg"
+version = "0.10.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "80d0f4e272c85def139476380b12f9ac60926689dd2e01d4923222f40580869d"
+dependencies = [
+ "winapi",
+]
+
+[[package]]
+name = "winsafe"
+version = "0.0.19"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d135d17ab770252ad95e9a872d365cf3090e3be864a34ab46f48555993efc904"
+
 [[package]]
 name = "wiremock"
 version = "0.6.4"
@@ -5986,6 +6297,23 @@ version = "0.6.1"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "ea2f10b9bb0928dfb1b42b65e1f9e36f7f54dbdf08457afefb38afcdec4fa2bb"
 
+[[package]]
+name = "x11rb"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d91ffca73ee7f68ce055750bf9f6eca0780b8c85eff9bc046a3b0da41755e12"
+dependencies = [
+ "gethostname",
+ "rustix 0.38.44",
+ "x11rb-protocol",
+]
+
+[[package]]
+name = "x11rb-protocol"
+version = "0.13.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ec107c4503ea0b4a98ef47356329af139c0a4f7750e621cf2973cd3385ebcb3d"
+
 [[package]]
 name = "yaml-rust"
 version = "0.4.5"

codex-rs/Cargo.toml

@@ -15,6 +15,8 @@ members = [
     "mcp-server",
     "mcp-types",
     "ollama",
+    "protocol",
+    "protocol-ts",
     "tui",
 ]
 resolver = "2"

codex-rs/apply-patch/Cargo.toml

@@ -6,6 +6,10 @@ version = { workspace = true }
 [lib]
 name = "codex_apply_patch"
 path = "src/lib.rs"
+ 
+[[bin]]
+name = "apply-patch"
+path = "src/main.rs"
 
 [lints]
 workspace = true
@@ -20,3 +24,4 @@ tree-sitter-bash = "0.25.0"
 [dev-dependencies]
 pretty_assertions = "1.4.1"
 tempfile = "3.13.0"
+assert_cmd = "2"

codex-rs/apply-patch/apply_patch_tool_instructions.md

@@ -1,17 +1,23 @@
-To edit files, ALWAYS use the `shell` tool with `apply_patch` CLI.  `apply_patch` effectively allows you to execute a diff/patch against a file, but the format of the diff specification is unique to this task, so pay careful attention to these instructions. To use the `apply_patch` CLI, you should call the shell tool with the following structure:
+## `apply_patch`
 
-```bash
-{"cmd": ["apply_patch", "<<'EOF'\\n*** Begin Patch\\n[YOUR_PATCH]\\n*** End Patch\\nEOF\\n"], "workdir": "..."}
-```
+Use the `apply_patch` shell command to edit files.
+Your patch language is a stripped‑down, file‑oriented diff format designed to be easy to parse and safe to apply. You can think of it as a high‑level envelope:
 
-Where [YOUR_PATCH] is the actual content of your patch, specified in the following V4A diff format.
+*** Begin Patch
+[ one or more file sections ]
+*** End Patch
 
-*** [ACTION] File: [path/to/file] -> ACTION can be one of Add, Update, or Delete.
-For each snippet of code that needs to be changed, repeat the following:
-[context_before] -> See below for further instructions on context.
-- [old_code] -> Precede the old code with a minus sign.
-+ [new_code] -> Precede the new, replacement code with a plus sign.
-[context_after] -> See below for further instructions on context.
+Within that envelope, you get a sequence of file operations.
+You MUST include a header to specify the action you are taking.
+Each operation starts with one of three headers:
+
+*** Add File: <path> - create a new file. Every following line is a + line (the initial contents).
+*** Delete File: <path> - remove an existing file. Nothing follows.
+*** Update File: <path> - patch an existing file in place (optionally with a rename).
+
+May be immediately followed by *** Move to: <new path> if you want to rename the file.
+Then one or more “hunks”, each introduced by @@ (optionally followed by a hunk header).
+Within a hunk each line starts with:
 
 For instructions on [context_before] and [context_after]:
 - By default, show 3 lines of code immediately above and 3 lines immediately below each change. If a change is within 3 lines of a previous change, do NOT duplicate the first change’s [context_after] lines in the second change’s [context_before] lines.
@@ -25,16 +31,45 @@ For instructions on [context_before] and [context_after]:
 - If a code block is repeated so many times in a class or function such that even a single `@@` statement and 3 lines of context cannot uniquely identify the snippet of code, you can use multiple `@@` statements to jump to the right context. For instance:
 
 @@ class BaseClass
-@@ 	def method():
+@@ 	 def method():
 [3 lines of pre-context]
 - [old_code]
 + [new_code]
 [3 lines of post-context]
 
-Note, then, that we do not use line numbers in this diff format, as the context is enough to uniquely identify code. An example of a message that you might pass as "input" to this function, in order to apply a patch, is shown below.
+The full grammar definition is below:
+Patch := Begin { FileOp } End
+Begin := "*** Begin Patch" NEWLINE
+End := "*** End Patch" NEWLINE
+FileOp := AddFile | DeleteFile | UpdateFile
+AddFile := "*** Add File: " path NEWLINE { "+" line NEWLINE }
+DeleteFile := "*** Delete File: " path NEWLINE
+UpdateFile := "*** Update File: " path NEWLINE [ MoveTo ] { Hunk }
+MoveTo := "*** Move to: " newPath NEWLINE
+Hunk := "@@" [ header ] NEWLINE { HunkLine } [ "*** End of File" NEWLINE ]
+HunkLine := (" " | "-" | "+") text NEWLINE
+
+A full patch can combine several operations:
+
+*** Begin Patch
+*** Add File: hello.txt
++Hello world
+*** Update File: src/app.py
+*** Move to: src/main.py
+@@ def greet():
+-print("Hi")
++print("Hello, world!")
+*** Delete File: obsolete.txt
+*** End Patch
+
+It is important to remember:
+
+- You must include a header with your intended action (Add/Delete/Update)
+- You must prefix new lines with `+` even when creating a new file
+- File references can only be relative, NEVER ABSOLUTE.
+
+You can invoke apply_patch like:
 
-```bash
-{"cmd": ["apply_patch", "<<'EOF'\\n*** Begin Patch\\n*** Update File: pygorithm/searching/binary_search.py\\n@@ class BaseClass\\n@@     def search():\\n-        pass\\n+        raise NotImplementedError()\\n@@ class Subclass\\n@@     def search():\\n-        pass\\n+        raise NotImplementedError()\\n*** End Patch\\nEOF\\n"], "workdir": "..."}
 ```
-
-File references can only be relative, NEVER ABSOLUTE. After the apply_patch command is run, it will always say "Done!", regardless of whether the patch was successfully applied or not. However, you can determine if there are issue and errors by looking at any warnings or logging lines printed BEFORE the "Done!" is output.
+shell {"command":["apply_patch","*** Begin Patch\n*** Add File: hello.txt\n+Hello, world!\n*** End Patch\n"]}
+```

codex-rs/apply-patch/src/lib.rs

@@ -22,6 +22,8 @@ use tree_sitter_bash::LANGUAGE as BASH;
 /// Detailed instructions for gpt-4.1 on how to use the `apply_patch` tool.
 pub const APPLY_PATCH_TOOL_INSTRUCTIONS: &str = include_str!("../apply_patch_tool_instructions.md");
 
+const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
+
 #[derive(Debug, Error, PartialEq)]
 pub enum ApplyPatchError {
     #[error(transparent)]
@@ -82,7 +84,6 @@ pub struct ApplyPatchArgs {
 }
 
 pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
-    const APPLY_PATCH_COMMANDS: [&str; 2] = ["apply_patch", "applypatch"];
     match argv {
         [cmd, body] if APPLY_PATCH_COMMANDS.contains(&cmd.as_str()) => match parse_patch(body) {
             Ok(source) => MaybeApplyPatch::Body(source),
@@ -91,7 +92,9 @@ pub fn maybe_parse_apply_patch(argv: &[String]) -> MaybeApplyPatch {
         [bash, flag, script]
             if bash == "bash"
                 && flag == "-lc"
-                && script.trim_start().starts_with("apply_patch") =>
+                && APPLY_PATCH_COMMANDS
+                    .iter()
+                    .any(|cmd| script.trim_start().starts_with(cmd)) =>
         {
             match extract_heredoc_body_from_apply_patch_command(script) {
                 Ok(body) => match parse_patch(&body) {
@@ -262,7 +265,10 @@ pub fn maybe_parse_apply_patch_verified(argv: &[String], cwd: &Path) -> MaybeApp
 fn extract_heredoc_body_from_apply_patch_command(
     src: &str,
 ) -> std::result::Result<String, ExtractHeredocError> {
-    if !src.trim_start().starts_with("apply_patch") {
+    if !APPLY_PATCH_COMMANDS
+        .iter()
+        .any(|cmd| src.trim_start().starts_with(cmd))
+    {
         return Err(ExtractHeredocError::CommandDidNotStartWithApplyPatch);
     }
 
@@ -415,12 +421,12 @@ fn apply_hunks_to_files(hunks: &[Hunk]) -> anyhow::Result<AffectedPaths> {
     for hunk in hunks {
         match hunk {
             Hunk::AddFile { path, contents } => {
-                if let Some(parent) = path.parent() {
-                    if !parent.as_os_str().is_empty() {
-                        std::fs::create_dir_all(parent).with_context(|| {
-                            format!("Failed to create parent directories for {}", path.display())
-                        })?;
-                    }
+                if let Some(parent) = path.parent()
+                    && !parent.as_os_str().is_empty()
+                {
+                    std::fs::create_dir_all(parent).with_context(|| {
+                        format!("Failed to create parent directories for {}", path.display())
+                    })?;
                 }
                 std::fs::write(path, contents)
                     .with_context(|| format!("Failed to write file {}", path.display()))?;
@@ -439,15 +445,12 @@ fn apply_hunks_to_files(hunks: &[Hunk]) -> anyhow::Result<AffectedPaths> {
                 let AppliedPatch { new_contents, .. } =
                     derive_new_contents_from_chunks(path, chunks)?;
                 if let Some(dest) = move_path {
-                    if let Some(parent) = dest.parent() {
-                        if !parent.as_os_str().is_empty() {
-                            std::fs::create_dir_all(parent).with_context(|| {
-                                format!(
-                                    "Failed to create parent directories for {}",
-                                    dest.display()
-                                )
-                            })?;
-                        }
+                    if let Some(parent) = dest.parent()
+                        && !parent.as_os_str().is_empty()
+                    {
+                        std::fs::create_dir_all(parent).with_context(|| {
+                            format!("Failed to create parent directories for {}", dest.display())
+                        })?;
                     }
                     std::fs::write(dest, new_contents)
                         .with_context(|| format!("Failed to write file {}", dest.display()))?;
@@ -529,9 +532,12 @@ fn compute_replacements(
         // If a chunk has a `change_context`, we use seek_sequence to find it, then
         // adjust our `line_index` to continue from there.
         if let Some(ctx_line) = &chunk.change_context {
-            if let Some(idx) =
-                seek_sequence::seek_sequence(original_lines, &[ctx_line.clone()], line_index, false)
-            {
+            if let Some(idx) = seek_sequence::seek_sequence(
+                original_lines,
+                std::slice::from_ref(ctx_line),
+                line_index,
+                false,
+            ) {
                 line_index = idx + 1;
             } else {
                 return Err(ApplyPatchError::ComputeReplacements(format!(
@@ -773,6 +779,33 @@ PATCH"#,
         }
     }
 
+    #[test]
+    fn test_heredoc_applypatch() {
+        let args = strs_to_strings(&[
+            "bash",
+            "-lc",
+            r#"applypatch <<'PATCH'
+*** Begin Patch
+*** Add File: foo
++hi
+*** End Patch
+PATCH"#,
+        ]);
+
+        match maybe_parse_apply_patch(&args) {
+            MaybeApplyPatch::Body(ApplyPatchArgs { hunks, patch: _ }) => {
+                assert_eq!(
+                    hunks,
+                    vec![Hunk::AddFile {
+                        path: PathBuf::from("foo"),
+                        contents: "hi\n".to_string()
+                    }]
+                );
+            }
+            result => panic!("expected MaybeApplyPatch::Body got {result:?}"),
+        }
+    }
+
     #[test]
     fn test_add_file_hunk_creates_file_with_contents() {
         let dir = tempdir().unwrap();

codex-rs/apply-patch/src/main.rs

@@ -0,0 +1,40 @@
+use std::io::Write;
+use std::process::ExitCode;
+
+fn main() -> ExitCode {
+    // Expect exactly one argument: the full apply_patch payload.
+    let mut args = std::env::args_os();
+    // argv[0]
+    let _argv0 = args.next();
+
+    let patch_arg = match args.next() {
+        Some(arg) => match arg.into_string() {
+            Ok(s) => s,
+            Err(_) => {
+                eprintln!("Error: apply-patch requires a UTF-8 PATCH argument.");
+                return ExitCode::from(1);
+            }
+        },
+        None => {
+            eprintln!("Usage: apply-patch '<apply_patch_payload>'");
+            return ExitCode::from(2);
+        }
+    };
+
+    // Refuse extra args to avoid ambiguity.
+    if args.next().is_some() {
+        eprintln!("Error: apply-patch accepts exactly one argument.");
+        return ExitCode::from(2);
+    }
+
+    let mut stdout = std::io::stdout();
+    let mut stderr = std::io::stderr();
+    match codex_apply_patch::apply_patch(&patch_arg, &mut stdout, &mut stderr) {
+        Ok(()) => {
+            // Flush to ensure output ordering when used in pipelines.
+            let _ = stdout.flush();
+            ExitCode::from(0)
+        }
+        Err(_) => ExitCode::from(1),
+    }
+}

codex-rs/apply-patch/tests/cli.rs

@@ -0,0 +1,48 @@
+#![allow(clippy::expect_used, clippy::unwrap_used)]
+use assert_cmd::prelude::*;
+use std::fs;
+use std::process::Command;
+use tempfile::tempdir;
+
+#[test]
+fn test_apply_patch_cli_add_and_update() -> anyhow::Result<()> {
+    let tmp = tempdir()?;
+    let file = "cli_test.txt";
+    let absolute_path = tmp.path().join(file);
+
+    // 1) Add a file
+    let add_patch = format!(
+        r#"*** Begin Patch
+*** Add File: {file}
++hello
+*** End Patch"#
+    );
+    Command::cargo_bin("apply-patch")
+        .expect("should find apply-patch binary")
+        .arg(add_patch)
+        .current_dir(tmp.path())
+        .assert()
+        .success()
+        .stdout(format!("Success. Updated the following files:\nA {file}\n"));
+    assert_eq!(fs::read_to_string(&absolute_path)?, "hello\n");
+
+    // 2) Update the file
+    let update_patch = format!(
+        r#"*** Begin Patch
+*** Update File: {file}
+@@
+-hello
++world
+*** End Patch"#
+    );
+    Command::cargo_bin("apply-patch")
+        .expect("should find apply-patch binary")
+        .arg(update_patch)
+        .current_dir(tmp.path())
+        .assert()
+        .success()
+        .stdout(format!("Success. Updated the following files:\nM {file}\n"));
+    assert_eq!(fs::read_to_string(&absolute_path)?, "world\n");
+
+    Ok(())
+}

codex-rs/arg0/src/lib.rs

@@ -89,10 +89,10 @@ const ILLEGAL_ENV_VAR_PREFIX: &str = "CODEX_";
 /// Security: Do not allow `.env` files to create or modify any variables
 /// with names starting with `CODEX_`.
 fn load_dotenv() {
-    if let Ok(codex_home) = codex_core::config::find_codex_home() {
-        if let Ok(iter) = dotenvy::from_path_iter(codex_home.join(".env")) {
-            set_filtered(iter);
-        }
+    if let Ok(codex_home) = codex_core::config::find_codex_home()
+        && let Ok(iter) = dotenvy::from_path_iter(codex_home.join(".env"))
+    {
+        set_filtered(iter);
     }
 
     if let Ok(iter) = dotenvy::dotenv_iter() {

codex-rs/chatgpt/src/chatgpt_token.rs

@@ -1,3 +1,4 @@
+use codex_login::AuthMode;
 use codex_login::CodexAuth;
 use std::path::Path;
 use std::sync::LazyLock;
@@ -19,7 +20,7 @@ pub fn set_chatgpt_token_data(value: TokenData) {
 
 /// Initialize the ChatGPT token from auth.json file
 pub async fn init_chatgpt_token_from_auth(codex_home: &Path) -> std::io::Result<()> {
-    let auth = CodexAuth::from_codex_home(codex_home)?;
+    let auth = CodexAuth::from_codex_home(codex_home, AuthMode::ChatGPT)?;
     if let Some(auth) = auth {
         let token_data = auth.get_token_data().await?;
         set_chatgpt_token_data(token_data);

codex-rs/cli/Cargo.toml

@@ -25,6 +25,7 @@ codex-core = { path = "../core" }
 codex-exec = { path = "../exec" }
 codex-login = { path = "../login" }
 codex-mcp-server = { path = "../mcp-server" }
+codex-protocol = { path = "../protocol" }
 codex-tui = { path = "../tui" }
 serde_json = "1"
 tokio = { version = "1", features = [
@@ -36,3 +37,4 @@ tokio = { version = "1", features = [
 ] }
 tracing = "0.1.41"
 tracing-subscriber = "0.3.19"
+codex-protocol-ts = { path = "../protocol-ts" }

codex-rs/cli/src/debug_sandbox.rs

@@ -3,11 +3,11 @@ use std::path::PathBuf;
 use codex_common::CliConfigOverrides;
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
-use codex_core::config_types::SandboxMode;
 use codex_core::exec_env::create_env;
 use codex_core::landlock::spawn_command_under_linux_sandbox;
 use codex_core::seatbelt::spawn_command_under_seatbelt;
 use codex_core::spawn::StdioPolicy;
+use codex_protocol::config_types::SandboxMode;
 
 use crate::LandlockCommand;
 use crate::SeatbeltCommand;

codex-rs/cli/src/login.rs

@@ -4,51 +4,30 @@ use codex_core::config::ConfigOverrides;
 use codex_login::AuthMode;
 use codex_login::CLIENT_ID;
 use codex_login::CodexAuth;
-use codex_login::LoginServerInfo;
 use codex_login::OPENAI_API_KEY_ENV_VAR;
 use codex_login::ServerOptions;
 use codex_login::login_with_api_key;
 use codex_login::logout;
-use codex_login::run_server_blocking_with_notify;
+use codex_login::run_login_server;
 use std::env;
-use std::path::Path;
-use std::sync::mpsc;
+use std::path::PathBuf;
 
-pub async fn login_with_chatgpt(codex_home: &Path) -> std::io::Result<()> {
-    let (tx, rx) = mpsc::channel::<LoginServerInfo>();
-    let client_id = CLIENT_ID;
-    let codex_home = codex_home.to_path_buf();
-    tokio::spawn(async move {
-        match rx.recv() {
-            Ok(LoginServerInfo {
-                auth_url,
-                actual_port,
-            }) => {
-                eprintln!(
-                    "Starting local login server on http://localhost:{actual_port}.\nIf your browser did not open, navigate to this URL to authenticate:\n\n{auth_url}",
-                );
-            }
-            _ => {
-                tracing::error!("Failed to receive login server info");
-            }
-        }
-    });
+pub async fn login_with_chatgpt(codex_home: PathBuf) -> std::io::Result<()> {
+    let opts = ServerOptions::new(codex_home, CLIENT_ID.to_string());
+    let server = run_login_server(opts)?;
 
-    tokio::task::spawn_blocking(move || {
-        let opts = ServerOptions::new(&codex_home, client_id);
-        run_server_blocking_with_notify(opts, Some(tx), None)
-    })
-    .await
-    .map_err(std::io::Error::other)??;
+    eprintln!(
+        "Starting local login server on http://localhost:{}.\nIf your browser did not open, navigate to this URL to authenticate:\n\n{}",
+        server.actual_port, server.auth_url,
+    );
 
-    eprintln!("Successfully logged in");
-    Ok(())
+    server.block_until_done().await
 }
 
 pub async fn run_login_with_chatgpt(cli_config_overrides: CliConfigOverrides) -> ! {
     let config = load_config_or_exit(cli_config_overrides);
 
-    match login_with_chatgpt(&config.codex_home).await {
+    match login_with_chatgpt(config.codex_home).await {
         Ok(_) => {
             eprintln!("Successfully logged in");
             std::process::exit(0);
@@ -81,18 +60,18 @@ pub async fn run_login_with_api_key(
 pub async fn run_login_status(cli_config_overrides: CliConfigOverrides) -> ! {
     let config = load_config_or_exit(cli_config_overrides);
 
-    match CodexAuth::from_codex_home(&config.codex_home) {
+    match CodexAuth::from_codex_home(&config.codex_home, config.preferred_auth_method) {
         Ok(Some(auth)) => match auth.mode {
             AuthMode::ApiKey => match auth.get_token().await {
                 Ok(api_key) => {
                     eprintln!("Logged in using an API key - {}", safe_format_key(&api_key));
 
-                    if let Ok(env_api_key) = env::var(OPENAI_API_KEY_ENV_VAR) {
-                        if env_api_key == api_key {
-                            eprintln!(
-                                "   API loaded from OPENAI_API_KEY environment variable or .env file"
-                            );
-                        }
+                    if let Ok(env_api_key) = env::var(OPENAI_API_KEY_ENV_VAR)
+                        && env_api_key == api_key
+                    {
+                        eprintln!(
+                            "   API loaded from OPENAI_API_KEY environment variable or .env file"
+                        );
                     }
                     std::process::exit(0);
                 }

codex-rs/cli/src/main.rs

@@ -72,6 +72,10 @@ enum Subcommand {
     /// Apply the latest diff produced by Codex agent as a `git apply` to your local working tree.
     #[clap(visible_alias = "a")]
     Apply(ApplyCommand),
+
+    /// Internal: generate TypeScript protocol bindings.
+    #[clap(hide = true)]
+    GenerateTs(GenerateTsCommand),
 }
 
 #[derive(Debug, Parser)]
@@ -120,6 +124,17 @@ struct LogoutCommand {
     config_overrides: CliConfigOverrides,
 }
 
+#[derive(Debug, Parser)]
+struct GenerateTsCommand {
+    /// Output directory where .ts files will be written
+    #[arg(short = 'o', long = "out", value_name = "DIR")]
+    out_dir: PathBuf,
+
+    /// Optional path to the Prettier executable to format generated files
+    #[arg(short = 'p', long = "prettier", value_name = "PRETTIER_BIN")]
+    prettier: Option<PathBuf>,
+}
+
 fn main() -> anyhow::Result<()> {
     arg0_dispatch_or_else(|codex_linux_sandbox_exe| async move {
         cli_main(codex_linux_sandbox_exe).await?;
@@ -144,7 +159,7 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
             codex_exec::run_main(exec_cli, codex_linux_sandbox_exe).await?;
         }
         Some(Subcommand::Mcp) => {
-            codex_mcp_server::run_main(codex_linux_sandbox_exe).await?;
+            codex_mcp_server::run_main(codex_linux_sandbox_exe, cli.config_overrides).await?;
         }
         Some(Subcommand::Login(mut login_cli)) => {
             prepend_config_flags(&mut login_cli.config_overrides, cli.config_overrides);
@@ -194,6 +209,9 @@ async fn cli_main(codex_linux_sandbox_exe: Option<PathBuf>) -> anyhow::Result<()
             prepend_config_flags(&mut apply_cli.config_overrides, cli.config_overrides);
             run_apply_command(apply_cli, None).await?;
         }
+        Some(Subcommand::GenerateTs(gen_cli)) => {
+            codex_protocol_ts::generate_ts(&gen_cli.out_dir, gen_cli.prettier.as_deref())?;
+        }
     }
 
     Ok(())

codex-rs/cli/src/proto.rs

@@ -9,6 +9,7 @@ use codex_core::config::ConfigOverrides;
 use codex_core::protocol::Event;
 use codex_core::protocol::EventMsg;
 use codex_core::protocol::Submission;
+use codex_login::AuthManager;
 use tokio::io::AsyncBufReadExt;
 use tokio::io::BufReader;
 use tracing::error;
@@ -36,7 +37,10 @@ pub async fn run_main(opts: ProtoCli) -> anyhow::Result<()> {
 
     let config = Config::load_with_cli_overrides(overrides_vec, ConfigOverrides::default())?;
     // Use conversation_manager API to start a conversation
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager = ConversationManager::new(AuthManager::shared(
+        config.codex_home.clone(),
+        config.preferred_auth_method,
+    ));
     let NewConversation {
         conversation_id: _,
         conversation,

codex-rs/clippy.toml

@@ -1,2 +1,9 @@
 allow-expect-in-tests = true
-allow-unwrap-in-tests = true
+allow-unwrap-in-tests = true
+disallowed-methods = [
+    { path = "ratatui::style::Color::Rgb", reason = "Use ANSI colors, which work better in various terminal themes." },
+    { path = "ratatui::style::Color::Indexed", reason = "Use ANSI colors, which work better in various terminal themes." },
+    { path = "ratatui::style::Stylize::white", reason = "Avoid hardcoding white; prefer default fg or dim/bold. Exception: Disable this rule if rendering over a hardcoded ANSI background." },
+    { path = "ratatui::style::Stylize::black", reason = "Avoid hardcoding black; prefer default fg or dim/bold. Exception: Disable this rule if rendering over a hardcoded ANSI background." },
+    { path = "ratatui::style::Stylize::yellow", reason = "Avoid yellow; prefer other colors in `tui/styles.md`." },
+]

codex-rs/common/Cargo.toml

@@ -9,6 +9,7 @@ workspace = true
 [dependencies]
 clap = { version = "4", features = ["derive", "wrap_help"], optional = true }
 codex-core = { path = "../core" }
+codex-protocol = { path = "../protocol" }
 serde = { version = "1", optional = true }
 toml = { version = "0.9", optional = true }
 

codex-rs/common/src/approval_presets.rs

@@ -0,0 +1,46 @@
+use codex_core::protocol::AskForApproval;
+use codex_core::protocol::SandboxPolicy;
+
+/// A simple preset pairing an approval policy with a sandbox policy.
+#[derive(Debug, Clone)]
+pub struct ApprovalPreset {
+    /// Stable identifier for the preset.
+    pub id: &'static str,
+    /// Display label shown in UIs.
+    pub label: &'static str,
+    /// Short human description shown next to the label in UIs.
+    pub description: &'static str,
+    /// Approval policy to apply.
+    pub approval: AskForApproval,
+    /// Sandbox policy to apply.
+    pub sandbox: SandboxPolicy,
+}
+
+/// Built-in list of approval presets that pair approval and sandbox policy.
+///
+/// Keep this UI-agnostic so it can be reused by both TUI and MCP server.
+pub fn builtin_approval_presets() -> Vec<ApprovalPreset> {
+    vec![
+        ApprovalPreset {
+            id: "read-only",
+            label: "Read Only",
+            description: "Codex can read files and answer questions. Codex requires approval to make edits, run commands, or access network",
+            approval: AskForApproval::OnRequest,
+            sandbox: SandboxPolicy::ReadOnly,
+        },
+        ApprovalPreset {
+            id: "auto",
+            label: "Auto",
+            description: "Codex can read files, make edits, and run commands in the workspace. Codex requires approval to work outside the workspace or access network",
+            approval: AskForApproval::OnRequest,
+            sandbox: SandboxPolicy::new_workspace_write_policy(),
+        },
+        ApprovalPreset {
+            id: "full-access",
+            label: "Full Access",
+            description: "Codex can read files, make edits, and run commands with network access, without approval. Exercise caution",
+            approval: AskForApproval::Never,
+            sandbox: SandboxPolicy::DangerFullAccess,
+        },
+    ]
+}

codex-rs/common/src/lib.rs

@@ -29,3 +29,8 @@ mod config_summary;
 pub use config_summary::create_config_summary_entries;
 // Shared fuzzy matcher (used by TUI selection popups and other UI filtering)
 pub mod fuzzy_match;
+// Shared model presets used by TUI and MCP server
+pub mod model_presets;
+// Shared approval presets (AskForApproval + Sandbox) used by TUI and MCP server
+// Not to be confused with AskForApproval, which we should probably rename to EscalationPolicy.
+pub mod approval_presets;

codex-rs/common/src/model_presets.rs

@@ -0,0 +1,54 @@
+use codex_core::protocol_config_types::ReasoningEffort;
+
+/// A simple preset pairing a model slug with a reasoning effort.
+#[derive(Debug, Clone, Copy)]
+pub struct ModelPreset {
+    /// Stable identifier for the preset.
+    pub id: &'static str,
+    /// Display label shown in UIs.
+    pub label: &'static str,
+    /// Short human description shown next to the label in UIs.
+    pub description: &'static str,
+    /// Model slug (e.g., "gpt-5").
+    pub model: &'static str,
+    /// Reasoning effort to apply for this preset.
+    pub effort: ReasoningEffort,
+}
+
+/// Built-in list of model presets that pair a model with a reasoning effort.
+///
+/// Keep this UI-agnostic so it can be reused by both TUI and MCP server.
+pub fn builtin_model_presets() -> &'static [ModelPreset] {
+    // Order reflects effort from minimal to high.
+    const PRESETS: &[ModelPreset] = &[
+        ModelPreset {
+            id: "gpt-5-minimal",
+            label: "gpt-5 minimal",
+            description: "— fastest responses with limited reasoning; ideal for coding, instructions, or lightweight tasks",
+            model: "gpt-5",
+            effort: ReasoningEffort::Minimal,
+        },
+        ModelPreset {
+            id: "gpt-5-low",
+            label: "gpt-5 low",
+            description: "— balances speed with some reasoning; useful for straightforward queries and short explanations",
+            model: "gpt-5",
+            effort: ReasoningEffort::Low,
+        },
+        ModelPreset {
+            id: "gpt-5-medium",
+            label: "gpt-5 medium",
+            description: "— default setting; provides a solid balance of reasoning depth and latency for general-purpose tasks",
+            model: "gpt-5",
+            effort: ReasoningEffort::Medium,
+        },
+        ModelPreset {
+            id: "gpt-5-high",
+            label: "gpt-5 high",
+            description: "— maximizes reasoning depth for complex or ambiguous problems",
+            model: "gpt-5",
+            effort: ReasoningEffort::High,
+        },
+    ];
+    PRESETS
+}

codex-rs/common/src/sandbox_mode_cli_arg.rs

@@ -7,7 +7,7 @@
 //! `config.toml`.
 
 use clap::ValueEnum;
-use codex_core::config_types::SandboxMode;
+use codex_protocol::config_types::SandboxMode;
 
 #[derive(Clone, Copy, Debug, ValueEnum)]
 #[value(rename_all = "kebab-case")]

codex-rs/config.md

@@ -149,6 +149,7 @@ approval_policy = "untrusted"
 ```
 
 If you want to be notified whenever a command fails, use "on-failure":
+
 ```toml
 # If the command fails when run in the sandbox, Codex asks for permission to
 # retry the command outside the sandbox.
@@ -156,12 +157,14 @@ approval_policy = "on-failure"
 ```
 
 If you want the model to run until it decides that it needs to ask you for escalated permissions, use "on-request":
+
 ```toml
 # The model decides when to escalate
 approval_policy = "on-request"
 ```
 
 Alternatively, you can have the model run until it is done, and never ask to run a command with escalated permissions:
+
 ```toml
 # User is never prompted: if the command fails, Codex will automatically try
 # something out. Note the `exec` subcommand always uses this mode.
@@ -217,17 +220,14 @@ Users can specify config values at multiple levels. Order of precedence is as fo
 
 ## model_reasoning_effort
 
-If the model name starts with `"o"` (as in `"o3"` or `"o4-mini"`) or `"codex"`, reasoning is enabled by default when using the Responses API. As explained in the [OpenAI Platform documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning), this can be set to:
+If the selected model is known to support reasoning (for example: `o3`, `o4-mini`, `codex-*`, `gpt-5`), reasoning is enabled by default when using the Responses API. As explained in the [OpenAI Platform documentation](https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning), this can be set to:
 
+- `"minimal"`
 - `"low"`
 - `"medium"` (default)
 - `"high"`
 
-To disable reasoning, set `model_reasoning_effort` to `"none"` in your config:
-
-```toml
-model_reasoning_effort = "none"  # disable reasoning
-```
+Note: to minimize reasoning, choose `"minimal"`.
 
 ## model_reasoning_summary
 
@@ -243,6 +243,25 @@ To disable reasoning summaries, set `model_reasoning_summary` to `"none"` in you
 model_reasoning_summary = "none"  # disable reasoning summaries
 ```
 
+## model_verbosity
+
+Controls output length/detail on GPT‑5 family models when using the Responses API. Supported values:
+
+- `"low"`
+- `"medium"` (default when omitted)
+- `"high"`
+
+When set, Codex includes a `text` object in the request payload with the configured verbosity, for example: `"text": { "verbosity": "low" }`.
+
+Example:
+
+```toml
+model = "gpt-5"
+model_verbosity = "low"
+```
+
+Note: This applies only to providers using the Responses API. Chat Completions providers are unaffected.
+
 ## model_supports_reasoning_summaries
 
 By default, `reasoning` is only set on requests to OpenAI models that are known to support them. To force `reasoning` to set on requests to the current model, you can force this behavior by setting the following in `config.toml`:
@@ -281,6 +300,9 @@ sandbox_mode = "workspace-write"
 exclude_tmpdir_env_var = false
 exclude_slash_tmp = false
 
+# Optional list of _additional_ writable roots beyond $TMPDIR and /tmp.
+writable_roots = ["/Users/YOU/.pyenv/shims"]
+
 # Allow the command being run inside the sandbox to make outbound network
 # requests. Disabled by default.
 network_access = false
@@ -297,6 +319,16 @@ This is reasonable to use if Codex is running in an environment that provides it
 
 Though using this option may also be necessary if you try to use Codex in environments where its native sandboxing mechanisms are unsupported, such as older Linux kernels or on Windows.
 
+## Approval presets
+
+Codex provides three main Approval Presets:
+
+- Read Only: Codex can read files and answer questions; edits, running commands, and network access require approval.
+- Auto: Codex can read files, make edits, and run commands in the workspace without approval; asks for approval outside the workspace or for network access.
+- Full Access: Full disk and network access without prompts; extremely risky.
+
+You can further customize how Codex runs at the command line using the `--ask-for-approval` and `--sandbox` options.
+
 ## mcp_servers
 
 Defines the list of MCP servers that Codex can consult for tool use. Currently, only servers that are launched by executing a program that communicate over stdio are supported. For servers that use the SSE transport, consider an adapter like [mcp-proxy](https://github.com/sparfenyuk/mcp-proxy).
@@ -498,10 +530,12 @@ hide_agent_reasoning = true   # defaults to false
 Surfaces the model’s raw chain-of-thought ("raw reasoning content") when available.
 
 Notes:
+
 - Only takes effect if the selected model/provider actually emits raw reasoning content. Many models do not. When unsupported, this option has no visible effect.
 - Raw reasoning may include intermediate thoughts or sensitive context. Enable only if acceptable for your workflow.
 
 Example:
+
 ```toml
 show_raw_agent_reasoning = true  # defaults to false
 ```

codex-rs/core/Cargo.toml

@@ -19,15 +19,16 @@ chrono = { version = "0.4", features = ["serde"] }
 codex-apply-patch = { path = "../apply-patch" }
 codex-login = { path = "../login" }
 codex-mcp-client = { path = "../mcp-client" }
+codex-protocol = { path = "../protocol" }
 dirs = "6"
 env-flags = "0.1.1"
 eventsource-stream = "0.2.3"
-fs2 = "0.4.3"
 futures = "0.3"
-libc = "0.2.174"
+libc = "0.2.175"
 mcp-types = { path = "../mcp-types" }
 mime_guess = "2.0"
 os_info = "3.12.0"
+portable-pty = "0.9.0"
 rand = "0.9"
 regex-lite = "0.1.6"
 reqwest = { version = "0.12", features = ["json", "stream"] }
@@ -71,6 +72,9 @@ openssl-sys = { version = "*", features = ["vendored"] }
 [target.aarch64-unknown-linux-musl.dependencies]
 openssl-sys = { version = "*", features = ["vendored"] }
 
+[target.'cfg(target_os = "windows")'.dependencies]
+which = "6"
+
 [dev-dependencies]
 assert_cmd = "2"
 core_test_support = { path = "tests/common" }

codex-rs/core/prompt.md

@@ -270,67 +270,6 @@ When using the shell, you must adhere to the following guidelines:
 - When searching for text or files, prefer using `rg` or `rg --files` respectively because `rg` is much faster than alternatives like `grep`. (If the `rg` command is not found, then use alternatives.)
 - Read files in chunks with a max chunk size of 250 lines. Do not use python scripts to attempt to output larger chunks of a file. Command line output will be truncated after 10 kilobytes or 256 lines of output, regardless of the command used.
 
-## `apply_patch`
-
-Your patch language is a stripped‑down, file‑oriented diff format designed to be easy to parse and safe to apply. You can think of it as a high‑level envelope:
-
-**_ Begin Patch
-[ one or more file sections ]
-_** End Patch
-
-Within that envelope, you get a sequence of file operations.
-You MUST include a header to specify the action you are taking.
-Each operation starts with one of three headers:
-
-**_ Add File: <path> - create a new file. Every following line is a + line (the initial contents).
-_** Delete File: <path> - remove an existing file. Nothing follows.
-\*\*\* Update File: <path> - patch an existing file in place (optionally with a rename).
-
-May be immediately followed by \*\*\* Move to: <new path> if you want to rename the file.
-Then one or more “hunks”, each introduced by @@ (optionally followed by a hunk header).
-Within a hunk each line starts with:
-
-- for inserted text,
-
-* for removed text, or
-  space ( ) for context.
-  At the end of a truncated hunk you can emit \*\*\* End of File.
-
-Patch := Begin { FileOp } End
-Begin := "**_ Begin Patch" NEWLINE
-End := "_** End Patch" NEWLINE
-FileOp := AddFile | DeleteFile | UpdateFile
-AddFile := "**_ Add File: " path NEWLINE { "+" line NEWLINE }
-DeleteFile := "_** Delete File: " path NEWLINE
-UpdateFile := "**_ Update File: " path NEWLINE [ MoveTo ] { Hunk }
-MoveTo := "_** Move to: " newPath NEWLINE
-Hunk := "@@" [ header ] NEWLINE { HunkLine } [ "*** End of File" NEWLINE ]
-HunkLine := (" " | "-" | "+") text NEWLINE
-
-A full patch can combine several operations:
-
-**_ Begin Patch
-_** Add File: hello.txt
-+Hello world
-**_ Update File: src/app.py
-_** Move to: src/main.py
-@@ def greet():
--print("Hi")
-+print("Hello, world!")
-**_ Delete File: obsolete.txt
-_** End Patch
-
-It is important to remember:
-
-- You must include a header with your intended action (Add/Delete/Update)
-- You must prefix new lines with `+` even when creating a new file
-
-You can invoke apply_patch like:
-
-```
-shell {"command":["apply_patch","*** Begin Patch\n*** Add File: hello.txt\n+Hello, world!\n*** End Patch\n"]}
-```
-
 ## `update_plan`
 
 A tool named `update_plan` is available to you. You can use it to keep an up‑to‑date, step‑by‑step plan for the task.

codex-rs/core/src/apply_patch.rs

@@ -1,14 +1,14 @@
 use crate::codex::Session;
-use crate::models::FunctionCallOutputPayload;
-use crate::models::ResponseInputItem;
+use crate::codex::TurnContext;
 use crate::protocol::FileChange;
 use crate::protocol::ReviewDecision;
 use crate::safety::SafetyCheck;
 use crate::safety::assess_patch_safety;
 use codex_apply_patch::ApplyPatchAction;
 use codex_apply_patch::ApplyPatchFileChange;
+use codex_protocol::models::FunctionCallOutputPayload;
+use codex_protocol::models::ResponseInputItem;
 use std::collections::HashMap;
-use std::path::Path;
 use std::path::PathBuf;
 
 pub const CODEX_APPLY_PATCH_ARG1: &str = "--codex-run-as-apply-patch";
@@ -41,17 +41,16 @@ impl From<ResponseInputItem> for InternalApplyPatchInvocation {
 
 pub(crate) async fn apply_patch(
     sess: &Session,
+    turn_context: &TurnContext,
     sub_id: &str,
     call_id: &str,
     action: ApplyPatchAction,
 ) -> InternalApplyPatchInvocation {
-    let writable_roots_snapshot = sess.get_writable_roots().to_vec();
-
     match assess_patch_safety(
         &action,
-        sess.get_approval_policy(),
-        &writable_roots_snapshot,
-        sess.get_cwd(),
+        turn_context.approval_policy,
+        &turn_context.sandbox_policy,
+        &turn_context.cwd,
     ) {
         SafetyCheck::AutoApprove { .. } => {
             InternalApplyPatchInvocation::DelegateToExec(ApplyPatchExec {
@@ -124,30 +123,3 @@ pub(crate) fn convert_apply_patch_to_protocol(
     }
     result
 }
-
-pub(crate) fn get_writable_roots(cwd: &Path) -> Vec<PathBuf> {
-    let mut writable_roots = Vec::new();
-    if cfg!(target_os = "macos") {
-        // On macOS, $TMPDIR is private to the user.
-        writable_roots.push(std::env::temp_dir());
-
-        // Allow pyenv to update its shims directory. Without this, any tool
-        // that happens to be managed by `pyenv` will fail with an error like:
-        //
-        //   pyenv: cannot rehash: $HOME/.pyenv/shims isn't writable
-        //
-        // which is emitted every time `pyenv` tries to run `rehash` (for
-        // example, after installing a new Python package that drops an entry
-        // point). Although the sandbox is intentionally read‑only by default,
-        // writing to the user's local `pyenv` directory is safe because it
-        // is already user‑writable and scoped to the current user account.
-        if let Ok(home_dir) = std::env::var("HOME") {
-            let pyenv_dir = PathBuf::from(home_dir).join(".pyenv");
-            writable_roots.push(pyenv_dir);
-        }
-    }
-
-    writable_roots.push(cwd.to_path_buf());
-
-    writable_roots
-}

codex-rs/core/src/chat_completions.rs

@@ -22,11 +22,11 @@ use crate::client_common::ResponseStream;
 use crate::error::CodexErr;
 use crate::error::Result;
 use crate::model_family::ModelFamily;
-use crate::models::ContentItem;
-use crate::models::ReasoningItemContent;
-use crate::models::ResponseItem;
 use crate::openai_tools::create_tools_json_for_chat_completions_api;
 use crate::util::backoff;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ReasoningItemContent;
+use codex_protocol::models::ResponseItem;
 
 /// Implementation for the classic Chat Completions API.
 pub(crate) async fn stream_chat_completions(
@@ -102,6 +102,33 @@ pub(crate) async fn stream_chat_completions(
                     "content": output.content,
                 }));
             }
+            ResponseItem::CustomToolCall {
+                id,
+                call_id: _,
+                name,
+                input,
+                status: _,
+            } => {
+                messages.push(json!({
+                    "role": "assistant",
+                    "content": null,
+                    "tool_calls": [{
+                        "id": id,
+                        "type": "custom",
+                        "custom": {
+                            "name": name,
+                            "input": input,
+                        }
+                    }]
+                }));
+            }
+            ResponseItem::CustomToolCallOutput { call_id, output } => {
+                messages.push(json!({
+                    "role": "tool",
+                    "tool_call_id": call_id,
+                    "content": output,
+                }));
+            }
             ResponseItem::Reasoning { .. } | ResponseItem::Other => {
                 // Omit these items from the conversation history.
                 continue;
@@ -290,13 +317,12 @@ async fn process_chat_sse<S>(
                 .get("delta")
                 .and_then(|d| d.get("content"))
                 .and_then(|c| c.as_str())
+                && !content.is_empty()
             {
-                if !content.is_empty() {
-                    assistant_text.push_str(content);
-                    let _ = tx_event
-                        .send(Ok(ResponseEvent::OutputTextDelta(content.to_string())))
-                        .await;
-                }
+                assistant_text.push_str(content);
+                let _ = tx_event
+                    .send(Ok(ResponseEvent::OutputTextDelta(content.to_string())))
+                    .await;
             }
 
             // Forward any reasoning/thinking deltas if present.
@@ -333,27 +359,25 @@ async fn process_chat_sse<S>(
                 .get("delta")
                 .and_then(|d| d.get("tool_calls"))
                 .and_then(|tc| tc.as_array())
+                && let Some(tool_call) = tool_calls.first()
             {
-                if let Some(tool_call) = tool_calls.first() {
-                    // Mark that we have an active function call in progress.
-                    fn_call_state.active = true;
+                // Mark that we have an active function call in progress.
+                fn_call_state.active = true;
 
-                    // Extract call_id if present.
-                    if let Some(id) = tool_call.get("id").and_then(|v| v.as_str()) {
-                        fn_call_state.call_id.get_or_insert_with(|| id.to_string());
+                // Extract call_id if present.
+                if let Some(id) = tool_call.get("id").and_then(|v| v.as_str()) {
+                    fn_call_state.call_id.get_or_insert_with(|| id.to_string());
+                }
+
+                // Extract function details if present.
+                if let Some(function) = tool_call.get("function") {
+                    if let Some(name) = function.get("name").and_then(|n| n.as_str()) {
+                        fn_call_state.name.get_or_insert_with(|| name.to_string());
                     }
 
-                    // Extract function details if present.
-                    if let Some(function) = tool_call.get("function") {
-                        if let Some(name) = function.get("name").and_then(|n| n.as_str()) {
-                            fn_call_state.name.get_or_insert_with(|| name.to_string());
-                        }
-
-                        if let Some(args_fragment) =
-                            function.get("arguments").and_then(|a| a.as_str())
-                        {
-                            fn_call_state.arguments.push_str(args_fragment);
-                        }
+                    if let Some(args_fragment) = function.get("arguments").and_then(|a| a.as_str())
+                    {
+                        fn_call_state.arguments.push_str(args_fragment);
                     }
                 }
             }
@@ -485,21 +509,23 @@ where
                     // do NOT emit yet. Forward any other item (e.g. FunctionCall) right
                     // away so downstream consumers see it.
 
-                    let is_assistant_delta = matches!(&item, crate::models::ResponseItem::Message { role, .. } if role == "assistant");
+                    let is_assistant_delta = matches!(&item, codex_protocol::models::ResponseItem::Message { role, .. } if role == "assistant");
 
                     if is_assistant_delta {
                         // Only use the final assistant message if we have not
                         // seen any deltas; otherwise, deltas already built the
                         // cumulative text and this would duplicate it.
-                        if this.cumulative.is_empty() {
-                            if let crate::models::ResponseItem::Message { content, .. } = &item {
-                                if let Some(text) = content.iter().find_map(|c| match c {
-                                    crate::models::ContentItem::OutputText { text } => Some(text),
-                                    _ => None,
-                                }) {
-                                    this.cumulative.push_str(text);
+                        if this.cumulative.is_empty()
+                            && let codex_protocol::models::ResponseItem::Message { content, .. } =
+                                &item
+                            && let Some(text) = content.iter().find_map(|c| match c {
+                                codex_protocol::models::ContentItem::OutputText { text } => {
+                                    Some(text)
                                 }
-                            }
+                                _ => None,
+                            })
+                        {
+                            this.cumulative.push_str(text);
                         }
 
                         // Swallow assistant message here; emit on Completed.
@@ -519,26 +545,27 @@ where
                     if !this.cumulative_reasoning.is_empty()
                         && matches!(this.mode, AggregateMode::AggregatedOnly)
                     {
-                        let aggregated_reasoning = crate::models::ResponseItem::Reasoning {
-                            id: String::new(),
-                            summary: Vec::new(),
-                            content: Some(vec![
-                                crate::models::ReasoningItemContent::ReasoningText {
-                                    text: std::mem::take(&mut this.cumulative_reasoning),
-                                },
-                            ]),
-                            encrypted_content: None,
-                        };
+                        let aggregated_reasoning =
+                            codex_protocol::models::ResponseItem::Reasoning {
+                                id: String::new(),
+                                summary: Vec::new(),
+                                content: Some(vec![
+                                    codex_protocol::models::ReasoningItemContent::ReasoningText {
+                                        text: std::mem::take(&mut this.cumulative_reasoning),
+                                    },
+                                ]),
+                                encrypted_content: None,
+                            };
                         this.pending
                             .push_back(ResponseEvent::OutputItemDone(aggregated_reasoning));
                         emitted_any = true;
                     }
 
                     if !this.cumulative.is_empty() {
-                        let aggregated_message = crate::models::ResponseItem::Message {
+                        let aggregated_message = codex_protocol::models::ResponseItem::Message {
                             id: None,
                             role: "assistant".to_string(),
-                            content: vec![crate::models::ContentItem::OutputText {
+                            content: vec![codex_protocol::models::ContentItem::OutputText {
                                 text: std::mem::take(&mut this.cumulative),
                             }],
                         };

codex-rs/core/src/client.rs

@@ -4,8 +4,8 @@ use std::sync::OnceLock;
 use std::time::Duration;
 
 use bytes::Bytes;
+use codex_login::AuthManager;
 use codex_login::AuthMode;
-use codex_login::CodexAuth;
 use eventsource_stream::Eventsource;
 use futures::prelude::*;
 use regex_lite::Regex;
@@ -28,20 +28,22 @@ use crate::client_common::ResponseEvent;
 use crate::client_common::ResponseStream;
 use crate::client_common::ResponsesApiRequest;
 use crate::client_common::create_reasoning_param_for_request;
+use crate::client_common::create_text_param_for_request;
 use crate::config::Config;
-use crate::config_types::ReasoningEffort as ReasoningEffortConfig;
-use crate::config_types::ReasoningSummary as ReasoningSummaryConfig;
 use crate::error::CodexErr;
 use crate::error::Result;
 use crate::error::UsageLimitReachedError;
 use crate::flags::CODEX_RS_SSE_FIXTURE;
+use crate::model_family::ModelFamily;
 use crate::model_provider_info::ModelProviderInfo;
 use crate::model_provider_info::WireApi;
-use crate::models::ResponseItem;
 use crate::openai_tools::create_tools_json_for_responses_api;
 use crate::protocol::TokenUsage;
 use crate::user_agent::get_codex_user_agent;
 use crate::util::backoff;
+use codex_protocol::config_types::ReasoningEffort as ReasoningEffortConfig;
+use codex_protocol::config_types::ReasoningSummary as ReasoningSummaryConfig;
+use codex_protocol::models::ResponseItem;
 use std::sync::Arc;
 
 #[derive(Debug, Deserialize)]
@@ -56,10 +58,10 @@ struct Error {
     message: Option<String>,
 }
 
-#[derive(Clone)]
+#[derive(Debug, Clone)]
 pub struct ModelClient {
     config: Arc<Config>,
-    auth: Option<CodexAuth>,
+    auth_manager: Option<Arc<AuthManager>>,
     client: reqwest::Client,
     provider: ModelProviderInfo,
     session_id: Uuid,
@@ -70,7 +72,7 @@ pub struct ModelClient {
 impl ModelClient {
     pub fn new(
         config: Arc<Config>,
-        auth: Option<CodexAuth>,
+        auth_manager: Option<Arc<AuthManager>>,
         provider: ModelProviderInfo,
         effort: ReasoningEffortConfig,
         summary: ReasoningSummaryConfig,
@@ -78,7 +80,7 @@ impl ModelClient {
     ) -> Self {
         Self {
             config,
-            auth,
+            auth_manager,
             client: reqwest::Client::new(),
             provider,
             session_id,
@@ -139,7 +141,8 @@ impl ModelClient {
             return stream_from_fixture(path, self.provider.clone()).await;
         }
 
-        let auth = self.auth.clone();
+        let auth_manager = self.auth_manager.clone();
+        let auth = auth_manager.as_ref().and_then(|m| m.auth());
 
         let auth_mode = auth.as_ref().map(|a| a.mode);
 
@@ -163,6 +166,19 @@ impl ModelClient {
 
         let input_with_instructions = prompt.get_formatted_input();
 
+        // Only include `text.verbosity` for GPT-5 family models
+        let text = if self.config.model_family.family == "gpt-5" {
+            create_text_param_for_request(self.config.model_verbosity)
+        } else {
+            if self.config.model_verbosity.is_some() {
+                warn!(
+                    "model_verbosity is set but ignored for non-gpt-5 model family: {}",
+                    self.config.model_family.family
+                );
+            }
+            None
+        };
+
         let payload = ResponsesApiRequest {
             model: &self.config.model,
             instructions: &full_instructions,
@@ -175,6 +191,7 @@ impl ModelClient {
             stream: true,
             include,
             prompt_cache_key: Some(self.session_id.to_string()),
+            text,
         };
 
         let mut attempt = 0;
@@ -207,11 +224,7 @@ impl ModelClient {
                 req_builder = req_builder.header("chatgpt-account-id", account_id);
             }
 
-            let originator = self
-                .config
-                .internal_originator
-                .as_deref()
-                .unwrap_or("codex_cli_rs");
+            let originator = &self.config.responses_originator_header;
             req_builder = req_builder.header("originator", originator);
             req_builder = req_builder.header("User-Agent", get_codex_user_agent(Some(originator)));
 
@@ -251,6 +264,13 @@ impl ModelClient {
                         .and_then(|v| v.to_str().ok())
                         .and_then(|s| s.parse::<u64>().ok());
 
+                    if status == StatusCode::UNAUTHORIZED
+                        && let Some(manager) = auth_manager.as_ref()
+                        && manager.auth().is_some()
+                    {
+                        let _ = manager.refresh_token().await;
+                    }
+
                     // The OpenAI Responses endpoint returns structured JSON bodies even for 4xx/5xx
                     // errors. When we bubble early with only the HTTP status the caller sees an opaque
                     // "unexpected status 400 Bad Request" which makes debugging nearly impossible.
@@ -258,7 +278,10 @@ impl ModelClient {
                     // exact error message (e.g. "Unknown parameter: 'input[0].metadata'"). The body is
                     // small and this branch only runs on error paths so the extra allocation is
                     // negligible.
-                    if !(status == StatusCode::TOO_MANY_REQUESTS || status.is_server_error()) {
+                    if !(status == StatusCode::TOO_MANY_REQUESTS
+                        || status == StatusCode::UNAUTHORIZED
+                        || status.is_server_error())
+                    {
                         // Surface the error body to callers. Use `unwrap_or_default` per Clippy.
                         let body = res.text().await.unwrap_or_default();
                         return Err(CodexErr::UnexpectedStatus(status, body));
@@ -311,6 +334,30 @@ impl ModelClient {
     pub fn get_provider(&self) -> ModelProviderInfo {
         self.provider.clone()
     }
+
+    /// Returns the currently configured model slug.
+    pub fn get_model(&self) -> String {
+        self.config.model.clone()
+    }
+
+    /// Returns the currently configured model family.
+    pub fn get_model_family(&self) -> ModelFamily {
+        self.config.model_family.clone()
+    }
+
+    /// Returns the current reasoning effort setting.
+    pub fn get_reasoning_effort(&self) -> ReasoningEffortConfig {
+        self.effort
+    }
+
+    /// Returns the current reasoning summary setting.
+    pub fn get_reasoning_summary(&self) -> ReasoningSummaryConfig {
+        self.summary
+    }
+
+    pub fn get_auth_manager(&self) -> Option<Arc<AuthManager>> {
+        self.auth_manager.clone()
+    }
 }
 
 #[derive(Debug, Deserialize, Serialize)]
@@ -528,6 +575,8 @@ async fn process_sse<S>(
             }
             "response.content_part.done"
             | "response.function_call_arguments.delta"
+            | "response.custom_tool_call_input.delta"
+            | "response.custom_tool_call_input.done" // also emitted as response.output_item.done
             | "response.in_progress"
             | "response.output_item.added"
             | "response.output_text.done" => {

codex-rs/core/src/client_common.rs

@@ -1,12 +1,13 @@
-use crate::config_types::ReasoningEffort as ReasoningEffortConfig;
-use crate::config_types::ReasoningSummary as ReasoningSummaryConfig;
+use crate::config_types::Verbosity as VerbosityConfig;
 use crate::error::Result;
 use crate::model_family::ModelFamily;
-use crate::models::ContentItem;
-use crate::models::ResponseItem;
 use crate::openai_tools::OpenAiTool;
 use crate::protocol::TokenUsage;
 use codex_apply_patch::APPLY_PATCH_TOOL_INSTRUCTIONS;
+use codex_protocol::config_types::ReasoningEffort as ReasoningEffortConfig;
+use codex_protocol::config_types::ReasoningSummary as ReasoningSummaryConfig;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ResponseItem;
 use futures::Stream;
 use serde::Serialize;
 use std::borrow::Cow;
@@ -47,7 +48,18 @@ impl Prompt {
             .as_deref()
             .unwrap_or(BASE_INSTRUCTIONS);
         let mut sections: Vec<&str> = vec![base];
-        if model.needs_special_apply_patch_instructions {
+
+        // When there are no custom instructions, add apply_patch_tool_instructions if either:
+        // - the model needs special instructions (4.1), or
+        // - there is no apply_patch tool present
+        let is_apply_patch_tool_present = self.tools.iter().any(|tool| match tool {
+            OpenAiTool::Function(f) => f.name == "apply_patch",
+            OpenAiTool::Freeform(f) => f.name == "apply_patch",
+            _ => false,
+        });
+        if self.base_instructions_override.is_none()
+            && (model.needs_special_apply_patch_instructions || !is_apply_patch_tool_present)
+        {
             sections.push(APPLY_PATCH_TOOL_INSTRUCTIONS);
         }
         Cow::Owned(sections.join("\n"))
@@ -85,51 +97,32 @@ pub enum ResponseEvent {
 
 #[derive(Debug, Serialize)]
 pub(crate) struct Reasoning {
-    pub(crate) effort: OpenAiReasoningEffort,
-    #[serde(skip_serializing_if = "Option::is_none")]
-    pub(crate) summary: Option<OpenAiReasoningSummary>,
+    pub(crate) effort: ReasoningEffortConfig,
+    pub(crate) summary: ReasoningSummaryConfig,
+}
+
+/// Controls under the `text` field in the Responses API for GPT-5.
+#[derive(Debug, Serialize, Default, Clone, Copy)]
+pub(crate) struct TextControls {
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(crate) verbosity: Option<OpenAiVerbosity>,
 }
 
-/// See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#get-started-with-reasoning
 #[derive(Debug, Serialize, Default, Clone, Copy)]
 #[serde(rename_all = "lowercase")]
-pub(crate) enum OpenAiReasoningEffort {
+pub(crate) enum OpenAiVerbosity {
     Low,
     #[default]
     Medium,
     High,
 }
 
-impl From<ReasoningEffortConfig> for Option<OpenAiReasoningEffort> {
-    fn from(effort: ReasoningEffortConfig) -> Self {
-        match effort {
-            ReasoningEffortConfig::Low => Some(OpenAiReasoningEffort::Low),
-            ReasoningEffortConfig::Medium => Some(OpenAiReasoningEffort::Medium),
-            ReasoningEffortConfig::High => Some(OpenAiReasoningEffort::High),
-            ReasoningEffortConfig::None => None,
-        }
-    }
-}
-
-/// A summary of the reasoning performed by the model. This can be useful for
-/// debugging and understanding the model's reasoning process.
-/// See https://platform.openai.com/docs/guides/reasoning?api-mode=responses#reasoning-summaries
-#[derive(Debug, Serialize, Default, Clone, Copy)]
-#[serde(rename_all = "lowercase")]
-pub(crate) enum OpenAiReasoningSummary {
-    #[default]
-    Auto,
-    Concise,
-    Detailed,
-}
-
-impl From<ReasoningSummaryConfig> for Option<OpenAiReasoningSummary> {
-    fn from(summary: ReasoningSummaryConfig) -> Self {
-        match summary {
-            ReasoningSummaryConfig::Auto => Some(OpenAiReasoningSummary::Auto),
-            ReasoningSummaryConfig::Concise => Some(OpenAiReasoningSummary::Concise),
-            ReasoningSummaryConfig::Detailed => Some(OpenAiReasoningSummary::Detailed),
-            ReasoningSummaryConfig::None => None,
+impl From<VerbosityConfig> for OpenAiVerbosity {
+    fn from(v: VerbosityConfig) -> Self {
+        match v {
+            VerbosityConfig::Low => OpenAiVerbosity::Low,
+            VerbosityConfig::Medium => OpenAiVerbosity::Medium,
+            VerbosityConfig::High => OpenAiVerbosity::High,
         }
     }
 }
@@ -154,6 +147,8 @@ pub(crate) struct ResponsesApiRequest<'a> {
     pub(crate) include: Vec<String>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub(crate) prompt_cache_key: Option<String>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub(crate) text: Option<TextControls>,
 }
 
 pub(crate) fn create_reasoning_param_for_request(
@@ -162,17 +157,20 @@ pub(crate) fn create_reasoning_param_for_request(
     summary: ReasoningSummaryConfig,
 ) -> Option<Reasoning> {
     if model_family.supports_reasoning_summaries {
-        let effort: Option<OpenAiReasoningEffort> = effort.into();
-        let effort = effort?;
-        Some(Reasoning {
-            effort,
-            summary: summary.into(),
-        })
+        Some(Reasoning { effort, summary })
     } else {
         None
     }
 }
 
+pub(crate) fn create_text_param_for_request(
+    verbosity: Option<VerbosityConfig>,
+) -> Option<TextControls> {
+    verbosity.map(|v| TextControls {
+        verbosity: Some(v.into()),
+    })
+}
+
 pub(crate) struct ResponseStream {
     pub(crate) rx_event: mpsc::Receiver<Result<ResponseEvent>>,
 }
@@ -201,4 +199,57 @@ mod tests {
         let full = prompt.get_full_instructions(&model_family);
         assert_eq!(full, expected);
     }
+
+    #[test]
+    fn serializes_text_verbosity_when_set() {
+        let input: Vec<ResponseItem> = vec![];
+        let tools: Vec<serde_json::Value> = vec![];
+        let req = ResponsesApiRequest {
+            model: "gpt-5",
+            instructions: "i",
+            input: &input,
+            tools: &tools,
+            tool_choice: "auto",
+            parallel_tool_calls: false,
+            reasoning: None,
+            store: true,
+            stream: true,
+            include: vec![],
+            prompt_cache_key: None,
+            text: Some(TextControls {
+                verbosity: Some(OpenAiVerbosity::Low),
+            }),
+        };
+
+        let v = serde_json::to_value(&req).expect("json");
+        assert_eq!(
+            v.get("text")
+                .and_then(|t| t.get("verbosity"))
+                .and_then(|s| s.as_str()),
+            Some("low")
+        );
+    }
+
+    #[test]
+    fn omits_text_when_not_set() {
+        let input: Vec<ResponseItem> = vec![];
+        let tools: Vec<serde_json::Value> = vec![];
+        let req = ResponsesApiRequest {
+            model: "gpt-5",
+            instructions: "i",
+            input: &input,
+            tools: &tools,
+            tool_choice: "auto",
+            parallel_tool_calls: false,
+            reasoning: None,
+            store: true,
+            stream: true,
+            include: vec![],
+            prompt_cache_key: None,
+            text: None,
+        };
+
+        let v = serde_json::to_value(&req).expect("json");
+        assert!(v.get("text").is_none());
+    }
 }

codex-rs/core/src/config.rs

@@ -1,14 +1,13 @@
 use crate::config_profile::ConfigProfile;
 use crate::config_types::History;
 use crate::config_types::McpServerConfig;
-use crate::config_types::ReasoningEffort;
-use crate::config_types::ReasoningSummary;
-use crate::config_types::SandboxMode;
 use crate::config_types::SandboxWorkspaceWrite;
 use crate::config_types::ShellEnvironmentPolicy;
 use crate::config_types::ShellEnvironmentPolicyToml;
 use crate::config_types::Tui;
 use crate::config_types::UriBasedFileOpener;
+use crate::config_types::Verbosity;
+use crate::git_info::resolve_root_git_project_for_trust;
 use crate::model_family::ModelFamily;
 use crate::model_family::find_family_for_model;
 use crate::model_provider_info::ModelProviderInfo;
@@ -16,6 +15,10 @@ use crate::model_provider_info::built_in_model_providers;
 use crate::openai_model_info::get_model_info;
 use crate::protocol::AskForApproval;
 use crate::protocol::SandboxPolicy;
+use codex_login::AuthMode;
+use codex_protocol::config_types::ReasoningEffort;
+use codex_protocol::config_types::ReasoningSummary;
+use codex_protocol::config_types::SandboxMode;
 use dirs::home_dir;
 use serde::Deserialize;
 use std::collections::HashMap;
@@ -34,6 +37,8 @@ pub(crate) const PROJECT_DOC_MAX_BYTES: usize = 32 * 1024; // 32 KiB
 
 const CONFIG_TOML_FILE: &str = "config.toml";
 
+const DEFAULT_RESPONSES_ORIGINATOR_HEADER: &str = "codex_cli_rs";
+
 /// Application configuration loaded from disk and merged with overrides.
 #[derive(Debug, Clone, PartialEq)]
 pub struct Config {
@@ -139,14 +144,17 @@ pub struct Config {
     /// When this program is invoked, arg0 will be set to `codex-linux-sandbox`.
     pub codex_linux_sandbox_exe: Option<PathBuf>,
 
-    /// If not "none", the value to use for `reasoning.effort` when making a
-    /// request using the Responses API.
+    /// Value to use for `reasoning.effort` when making a request using the
+    /// Responses API.
     pub model_reasoning_effort: ReasoningEffort,
 
     /// If not "none", the value to use for `reasoning.summary` when making a
     /// request using the Responses API.
     pub model_reasoning_summary: ReasoningSummary,
 
+    /// Optional verbosity control for GPT-5 models (Responses API `text.verbosity`).
+    pub model_verbosity: Option<Verbosity>,
+
     /// Base URL for requests to ChatGPT (as opposed to the OpenAI API).
     pub chatgpt_base_url: String,
 
@@ -156,8 +164,18 @@ pub struct Config {
     /// Include an experimental plan tool that the model can use to update its current plan and status of each step.
     pub include_plan_tool: bool,
 
+    /// Include the `apply_patch` tool for models that benefit from invoking
+    /// file edits as a structured tool call. When unset, this falls back to the
+    /// model family's default preference.
+    pub include_apply_patch_tool: bool,
+
     /// The value for the `originator` header included with Responses API requests.
-    pub internal_originator: Option<String>,
+    pub responses_originator_header: String,
+
+    /// If set to `true`, the API key will be signed with the `originator` header.
+    pub preferred_auth_method: AuthMode,
+
+    pub use_experimental_streamable_shell_tool: bool,
 }
 
 impl Config {
@@ -248,10 +266,61 @@ pub fn set_project_trusted(codex_home: &Path, project_path: &Path) -> anyhow::Re
         Err(e) => return Err(e.into()),
     };
 
-    // Mark the project as trusted. toml_edit is very good at handling
-    // missing properties
+    // Ensure we render a human-friendly structure:
+    //
+    // [projects]
+    // [projects."/path/to/project"]
+    // trust_level = "trusted"
+    //
+    // rather than inline tables like:
+    //
+    // [projects]
+    // "/path/to/project" = { trust_level = "trusted" }
     let project_key = project_path.to_string_lossy().to_string();
-    doc["projects"][project_key.as_str()]["trust_level"] = toml_edit::value("trusted");
+
+    // Ensure top-level `projects` exists as a non-inline, explicit table. If it
+    // exists but was previously represented as a non-table (e.g., inline),
+    // replace it with an explicit table.
+    let mut created_projects_table = false;
+    {
+        let root = doc.as_table_mut();
+        let needs_table = !root.contains_key("projects")
+            || root.get("projects").and_then(|i| i.as_table()).is_none();
+        if needs_table {
+            root.insert("projects", toml_edit::table());
+            created_projects_table = true;
+        }
+    }
+    let Some(projects_tbl) = doc["projects"].as_table_mut() else {
+        return Err(anyhow::anyhow!(
+            "projects table missing after initialization"
+        ));
+    };
+
+    // If we created the `projects` table ourselves, keep it implicit so we
+    // don't render a standalone `[projects]` header.
+    if created_projects_table {
+        projects_tbl.set_implicit(true);
+    }
+
+    // Ensure the per-project entry is its own explicit table. If it exists but
+    // is not a table (e.g., an inline table), replace it with an explicit table.
+    let needs_proj_table = !projects_tbl.contains_key(project_key.as_str())
+        || projects_tbl
+            .get(project_key.as_str())
+            .and_then(|i| i.as_table())
+            .is_none();
+    if needs_proj_table {
+        projects_tbl.insert(project_key.as_str(), toml_edit::table());
+    }
+    let Some(proj_tbl) = projects_tbl
+        .get_mut(project_key.as_str())
+        .and_then(|i| i.as_table_mut())
+    else {
+        return Err(anyhow::anyhow!("project table missing for {}", project_key));
+    };
+    proj_tbl.set_implicit(false);
+    proj_tbl["trust_level"] = toml_edit::value("trusted");
 
     // ensure codex_home exists
     std::fs::create_dir_all(codex_home)?;
@@ -387,6 +456,8 @@ pub struct ConfigToml {
 
     pub model_reasoning_effort: Option<ReasoningEffort>,
     pub model_reasoning_summary: Option<ReasoningSummary>,
+    /// Optional verbosity control for GPT-5 models (Responses API `text.verbosity`).
+    pub model_verbosity: Option<Verbosity>,
 
     /// Override to force-enable reasoning summaries for the configured model.
     pub model_supports_reasoning_summaries: Option<bool>,
@@ -400,10 +471,15 @@ pub struct ConfigToml {
     /// Experimental path to a file whose contents replace the built-in BASE_INSTRUCTIONS.
     pub experimental_instructions_file: Option<PathBuf>,
 
+    pub experimental_use_exec_command_tool: Option<bool>,
+
     /// The value for the `originator` header included with Responses API requests.
-    pub internal_originator: Option<String>,
+    pub responses_originator_header_internal_override: Option<String>,
 
     pub projects: Option<HashMap<String, ProjectConfig>>,
+
+    /// If set to `true`, the API key will be signed with the `originator` header.
+    pub preferred_auth_method: Option<AuthMode>,
 }
 
 #[derive(Deserialize, Debug, Clone, PartialEq, Eq)]
@@ -440,10 +516,27 @@ impl ConfigToml {
     pub fn is_cwd_trusted(&self, resolved_cwd: &Path) -> bool {
         let projects = self.projects.clone().unwrap_or_default();
 
-        projects
-            .get(&resolved_cwd.to_string_lossy().to_string())
-            .map(|p| p.trust_level.clone().unwrap_or("".to_string()) == "trusted")
-            .unwrap_or(false)
+        let is_path_trusted = |path: &Path| {
+            let path_str = path.to_string_lossy().to_string();
+            projects
+                .get(&path_str)
+                .map(|p| p.trust_level.as_deref() == Some("trusted"))
+                .unwrap_or(false)
+        };
+
+        // Fast path: exact cwd match
+        if is_path_trusted(resolved_cwd) {
+            return true;
+        }
+
+        // If cwd lives inside a git worktree, check whether the root git project
+        // (the primary repository working directory) is trusted. This lets
+        // worktrees inherit trust from the main project.
+        if let Some(root_project) = resolve_root_git_project_for_trust(resolved_cwd) {
+            return is_path_trusted(&root_project);
+        }
+
+        false
     }
 
     pub fn get_config_profile(
@@ -480,6 +573,7 @@ pub struct ConfigOverrides {
     pub codex_linux_sandbox_exe: Option<PathBuf>,
     pub base_instructions: Option<String>,
     pub include_plan_tool: Option<bool>,
+    pub include_apply_patch_tool: Option<bool>,
     pub disable_response_storage: Option<bool>,
     pub show_raw_agent_reasoning: Option<bool>,
 }
@@ -505,6 +599,7 @@ impl Config {
             codex_linux_sandbox_exe,
             base_instructions,
             include_plan_tool,
+            include_apply_patch_tool,
             disable_response_storage,
             show_raw_agent_reasoning,
         } = overrides;
@@ -581,6 +676,7 @@ impl Config {
                 needs_special_apply_patch_instructions: false,
                 supports_reasoning_summaries,
                 uses_local_shell_tool: false,
+                apply_patch_tool_type: None,
             }
         });
 
@@ -607,6 +703,10 @@ impl Config {
             Self::get_base_instructions(experimental_instructions_path, &resolved_cwd)?;
         let base_instructions = base_instructions.or(file_base_instructions);
 
+        let responses_originator_header: String = cfg
+            .responses_originator_header_internal_override
+            .unwrap_or(DEFAULT_RESPONSES_ORIGINATOR_HEADER.to_owned());
+
         let config = Self {
             model,
             model_family,
@@ -651,7 +751,7 @@ impl Config {
                 .model_reasoning_summary
                 .or(cfg.model_reasoning_summary)
                 .unwrap_or_default(),
-
+            model_verbosity: config_profile.model_verbosity.or(cfg.model_verbosity),
             chatgpt_base_url: config_profile
                 .chatgpt_base_url
                 .or(cfg.chatgpt_base_url)
@@ -659,7 +759,12 @@ impl Config {
 
             experimental_resume,
             include_plan_tool: include_plan_tool.unwrap_or(false),
-            internal_originator: cfg.internal_originator,
+            include_apply_patch_tool: include_apply_patch_tool.unwrap_or(false),
+            responses_originator_header,
+            preferred_auth_method: cfg.preferred_auth_method.unwrap_or(AuthMode::ChatGPT),
+            use_experimental_streamable_shell_tool: cfg
+                .experimental_use_exec_command_tool
+                .unwrap_or(false),
         };
         Ok(config)
     }
@@ -739,10 +844,10 @@ fn default_model() -> String {
 pub fn find_codex_home() -> std::io::Result<PathBuf> {
     // Honor the `CODEX_HOME` environment variable when it is set to allow users
     // (and tests) to override the default location.
-    if let Ok(val) = std::env::var("CODEX_HOME") {
-        if !val.is_empty() {
-            return PathBuf::from(val).canonicalize();
-        }
+    if let Ok(val) = std::env::var("CODEX_HOME")
+        && !val.is_empty()
+    {
+        return PathBuf::from(val).canonicalize();
     }
 
     let mut p = home_dir().ok_or_else(|| {
@@ -1018,11 +1123,15 @@ disable_response_storage = true
                 show_raw_agent_reasoning: false,
                 model_reasoning_effort: ReasoningEffort::High,
                 model_reasoning_summary: ReasoningSummary::Detailed,
+                model_verbosity: None,
                 chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
                 experimental_resume: None,
                 base_instructions: None,
                 include_plan_tool: false,
-                internal_originator: None,
+                include_apply_patch_tool: false,
+                responses_originator_header: "codex_cli_rs".to_string(),
+                preferred_auth_method: AuthMode::ChatGPT,
+                use_experimental_streamable_shell_tool: false,
             },
             o3_profile_config
         );
@@ -1069,11 +1178,15 @@ disable_response_storage = true
             show_raw_agent_reasoning: false,
             model_reasoning_effort: ReasoningEffort::default(),
             model_reasoning_summary: ReasoningSummary::default(),
+            model_verbosity: None,
             chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
             experimental_resume: None,
             base_instructions: None,
             include_plan_tool: false,
-            internal_originator: None,
+            include_apply_patch_tool: false,
+            responses_originator_header: "codex_cli_rs".to_string(),
+            preferred_auth_method: AuthMode::ChatGPT,
+            use_experimental_streamable_shell_tool: false,
         };
 
         assert_eq!(expected_gpt3_profile_config, gpt3_profile_config);
@@ -1135,15 +1248,89 @@ disable_response_storage = true
             show_raw_agent_reasoning: false,
             model_reasoning_effort: ReasoningEffort::default(),
             model_reasoning_summary: ReasoningSummary::default(),
+            model_verbosity: None,
             chatgpt_base_url: "https://chatgpt.com/backend-api/".to_string(),
             experimental_resume: None,
             base_instructions: None,
             include_plan_tool: false,
-            internal_originator: None,
+            include_apply_patch_tool: false,
+            responses_originator_header: "codex_cli_rs".to_string(),
+            preferred_auth_method: AuthMode::ChatGPT,
+            use_experimental_streamable_shell_tool: false,
         };
 
         assert_eq!(expected_zdr_profile_config, zdr_profile_config);
 
         Ok(())
     }
+
+    #[test]
+    fn test_set_project_trusted_writes_explicit_tables() -> anyhow::Result<()> {
+        let codex_home = TempDir::new().unwrap();
+        let project_dir = TempDir::new().unwrap();
+
+        // Call the function under test
+        set_project_trusted(codex_home.path(), project_dir.path())?;
+
+        // Read back the generated config.toml and assert exact contents
+        let config_path = codex_home.path().join(CONFIG_TOML_FILE);
+        let contents = std::fs::read_to_string(&config_path)?;
+
+        let raw_path = project_dir.path().to_string_lossy();
+        let path_str = if raw_path.contains('\\') {
+            format!("'{}'", raw_path)
+        } else {
+            format!("\"{}\"", raw_path)
+        };
+        let expected = format!(
+            r#"[projects.{path_str}]
+trust_level = "trusted"
+"#
+        );
+        assert_eq!(contents, expected);
+
+        Ok(())
+    }
+
+    #[test]
+    fn test_set_project_trusted_converts_inline_to_explicit() -> anyhow::Result<()> {
+        let codex_home = TempDir::new().unwrap();
+        let project_dir = TempDir::new().unwrap();
+
+        // Seed config.toml with an inline project entry under [projects]
+        let config_path = codex_home.path().join(CONFIG_TOML_FILE);
+        let raw_path = project_dir.path().to_string_lossy();
+        let path_str = if raw_path.contains('\\') {
+            format!("'{}'", raw_path)
+        } else {
+            format!("\"{}\"", raw_path)
+        };
+        // Use a quoted key so backslashes don't require escaping on Windows
+        let initial = format!(
+            r#"[projects]
+{path_str} = {{ trust_level = "untrusted" }}
+"#
+        );
+        std::fs::create_dir_all(codex_home.path())?;
+        std::fs::write(&config_path, initial)?;
+
+        // Run the function; it should convert to explicit tables and set trusted
+        set_project_trusted(codex_home.path(), project_dir.path())?;
+
+        let contents = std::fs::read_to_string(&config_path)?;
+
+        // Assert exact output after conversion to explicit table
+        let expected = format!(
+            r#"[projects]
+
+[projects.{path_str}]
+trust_level = "trusted"
+"#
+        );
+        assert_eq!(contents, expected);
+
+        Ok(())
+    }
+
+    // No test enforcing the presence of a standalone [projects] header.
 }

codex-rs/core/src/config_profile.rs

@@ -1,9 +1,10 @@
 use serde::Deserialize;
 use std::path::PathBuf;
 
-use crate::config_types::ReasoningEffort;
-use crate::config_types::ReasoningSummary;
+use crate::config_types::Verbosity;
 use crate::protocol::AskForApproval;
+use codex_protocol::config_types::ReasoningEffort;
+use codex_protocol::config_types::ReasoningSummary;
 
 /// Collection of common configuration options that a user can define as a unit
 /// in `config.toml`.
@@ -17,6 +18,7 @@ pub struct ConfigProfile {
     pub disable_response_storage: Option<bool>,
     pub model_reasoning_effort: Option<ReasoningEffort>,
     pub model_reasoning_summary: Option<ReasoningSummary>,
+    pub model_verbosity: Option<Verbosity>,
     pub chatgpt_base_url: Option<String>,
     pub experimental_instructions_file: Option<PathBuf>,
 }

codex-rs/core/src/config_types.rs

@@ -5,11 +5,11 @@
 
 use std::collections::HashMap;
 use std::path::PathBuf;
-use strum_macros::Display;
 use wildmatch::WildMatchPattern;
 
 use serde::Deserialize;
 use serde::Serialize;
+use strum_macros::Display;
 
 #[derive(Deserialize, Debug, Clone, PartialEq)]
 pub struct McpServerConfig {
@@ -78,21 +78,6 @@ pub enum HistoryPersistence {
 #[derive(Deserialize, Debug, Clone, PartialEq, Default)]
 pub struct Tui {}
 
-#[derive(Deserialize, Debug, Clone, Copy, PartialEq, Default, Serialize, Display)]
-#[serde(rename_all = "kebab-case")]
-#[strum(serialize_all = "kebab-case")]
-pub enum SandboxMode {
-    #[serde(rename = "read-only")]
-    #[default]
-    ReadOnly,
-
-    #[serde(rename = "workspace-write")]
-    WorkspaceWrite,
-
-    #[serde(rename = "danger-full-access")]
-    DangerFullAccess,
-}
-
 #[derive(Deserialize, Debug, Clone, PartialEq, Default)]
 pub struct SandboxWorkspaceWrite {
     #[serde(default)]
@@ -228,3 +213,15 @@ pub enum ReasoningSummary {
     /// Option to disable reasoning summaries.
     None,
 }
+
+/// Controls output length/detail on GPT-5 models via the Responses API.
+/// Serialized with lowercase values to match the OpenAI API.
+#[derive(Debug, Serialize, Deserialize, Default, Clone, Copy, PartialEq, Eq, Display)]
+#[serde(rename_all = "lowercase")]
+#[strum(serialize_all = "lowercase")]
+pub enum Verbosity {
+    Low,
+    #[default]
+    Medium,
+    High,
+}

codex-rs/core/src/conversation_history.rs

@@ -1,4 +1,4 @@
-use crate::models::ResponseItem;
+use codex_protocol::models::ResponseItem;
 
 /// Transcript of conversation history
 #[derive(Debug, Clone, Default)]
@@ -66,7 +66,7 @@ impl ConversationHistory {
                 self.items.push(ResponseItem::Message {
                     id: None,
                     role: "assistant".to_string(),
-                    content: vec![crate::models::ContentItem::OutputText {
+                    content: vec![codex_protocol::models::ContentItem::OutputText {
                         text: delta.to_string(),
                     }],
                 });
@@ -110,6 +110,8 @@ fn is_api_message(message: &ResponseItem) -> bool {
         ResponseItem::Message { role, .. } => role.as_str() != "system",
         ResponseItem::FunctionCallOutput { .. }
         | ResponseItem::FunctionCall { .. }
+        | ResponseItem::CustomToolCall { .. }
+        | ResponseItem::CustomToolCallOutput { .. }
         | ResponseItem::LocalShellCall { .. }
         | ResponseItem::Reasoning { .. } => true,
         ResponseItem::Other => false,
@@ -118,11 +120,11 @@ fn is_api_message(message: &ResponseItem) -> bool {
 
 /// Helper to append the textual content from `src` into `dst` in place.
 fn append_text_content(
-    dst: &mut Vec<crate::models::ContentItem>,
-    src: &Vec<crate::models::ContentItem>,
+    dst: &mut Vec<codex_protocol::models::ContentItem>,
+    src: &Vec<codex_protocol::models::ContentItem>,
 ) {
     for c in src {
-        if let crate::models::ContentItem::OutputText { text } = c {
+        if let codex_protocol::models::ContentItem::OutputText { text } = c {
             append_text_delta(dst, text);
         }
     }
@@ -130,15 +132,15 @@ fn append_text_content(
 
 /// Append a single text delta to the last OutputText item in `content`, or
 /// push a new OutputText item if none exists.
-fn append_text_delta(content: &mut Vec<crate::models::ContentItem>, delta: &str) {
-    if let Some(crate::models::ContentItem::OutputText { text }) = content
+fn append_text_delta(content: &mut Vec<codex_protocol::models::ContentItem>, delta: &str) {
+    if let Some(codex_protocol::models::ContentItem::OutputText { text }) = content
         .iter_mut()
         .rev()
-        .find(|c| matches!(c, crate::models::ContentItem::OutputText { .. }))
+        .find(|c| matches!(c, codex_protocol::models::ContentItem::OutputText { .. }))
     {
         text.push_str(delta);
     } else {
-        content.push(crate::models::ContentItem::OutputText {
+        content.push(codex_protocol::models::ContentItem::OutputText {
             text: delta.to_string(),
         });
     }
@@ -147,7 +149,7 @@ fn append_text_delta(content: &mut Vec<crate::models::ContentItem>, delta: &str)
 #[cfg(test)]
 mod tests {
     use super::*;
-    use crate::models::ContentItem;
+    use codex_protocol::models::ContentItem;
 
     fn assistant_msg(text: &str) -> ResponseItem {
         ResponseItem::Message {

codex-rs/core/src/conversation_manager.rs

@@ -1,6 +1,7 @@
 use std::collections::HashMap;
 use std::sync::Arc;
 
+use codex_login::AuthManager;
 use codex_login::CodexAuth;
 use tokio::sync::RwLock;
 use uuid::Uuid;
@@ -15,6 +16,7 @@ use crate::error::Result as CodexResult;
 use crate::protocol::Event;
 use crate::protocol::EventMsg;
 use crate::protocol::SessionConfiguredEvent;
+use codex_protocol::models::ResponseItem;
 
 /// Represents a newly created Codex conversation, including the first event
 /// (which is [`EventMsg::SessionConfigured`]).
@@ -28,34 +30,48 @@ pub struct NewConversation {
 /// maintaining them in memory.
 pub struct ConversationManager {
     conversations: Arc<RwLock<HashMap<Uuid, Arc<CodexConversation>>>>,
-}
-
-impl Default for ConversationManager {
-    fn default() -> Self {
-        Self {
-            conversations: Arc::new(RwLock::new(HashMap::new())),
-        }
-    }
+    auth_manager: Arc<AuthManager>,
 }
 
 impl ConversationManager {
-    pub async fn new_conversation(&self, config: Config) -> CodexResult<NewConversation> {
-        let auth = CodexAuth::from_codex_home(&config.codex_home)?;
-        self.new_conversation_with_auth(config, auth).await
+    pub fn new(auth_manager: Arc<AuthManager>) -> Self {
+        Self {
+            conversations: Arc::new(RwLock::new(HashMap::new())),
+            auth_manager,
+        }
     }
 
-    /// Used for integration tests: should not be used by ordinary business
-    /// logic.
-    pub async fn new_conversation_with_auth(
+    /// Construct with a dummy AuthManager containing the provided CodexAuth.
+    /// Used for integration tests: should not be used by ordinary business logic.
+    pub fn with_auth(auth: CodexAuth) -> Self {
+        Self::new(codex_login::AuthManager::from_auth_for_testing(auth))
+    }
+
+    pub async fn new_conversation(&self, config: Config) -> CodexResult<NewConversation> {
+        self.spawn_conversation(config, self.auth_manager.clone())
+            .await
+    }
+
+    async fn spawn_conversation(
         &self,
         config: Config,
-        auth: Option<CodexAuth>,
+        auth_manager: Arc<AuthManager>,
     ) -> CodexResult<NewConversation> {
         let CodexSpawnOk {
             codex,
             session_id: conversation_id,
-        } = Codex::spawn(config, auth).await?;
+        } = {
+            let initial_history = None;
+            Codex::spawn(config, auth_manager, initial_history).await?
+        };
+        self.finalize_spawn(codex, conversation_id).await
+    }
 
+    async fn finalize_spawn(
+        &self,
+        codex: Codex,
+        conversation_id: Uuid,
+    ) -> CodexResult<NewConversation> {
         // The first event must be `SessionInitialized`. Validate and forward it
         // to the caller so that they can display it in the conversation
         // history.
@@ -93,4 +109,120 @@ impl ConversationManager {
             .cloned()
             .ok_or_else(|| CodexErr::ConversationNotFound(conversation_id))
     }
+
+    /// Fork an existing conversation by dropping the last `drop_last_messages`
+    /// user/assistant messages from its transcript and starting a new
+    /// conversation with identical configuration (unless overridden by the
+    /// caller's `config`). The new conversation will have a fresh id.
+    pub async fn fork_conversation(
+        &self,
+        conversation_history: Vec<ResponseItem>,
+        num_messages_to_drop: usize,
+        config: Config,
+    ) -> CodexResult<NewConversation> {
+        // Compute the prefix up to the cut point.
+        let truncated_history =
+            truncate_after_dropping_last_messages(conversation_history, num_messages_to_drop);
+
+        // Spawn a new conversation with the computed initial history.
+        let auth_manager = self.auth_manager.clone();
+        let CodexSpawnOk {
+            codex,
+            session_id: conversation_id,
+        } = Codex::spawn(config, auth_manager, Some(truncated_history)).await?;
+
+        self.finalize_spawn(codex, conversation_id).await
+    }
+}
+
+/// Return a prefix of `items` obtained by dropping the last `n` user messages
+/// and all items that follow them.
+fn truncate_after_dropping_last_messages(items: Vec<ResponseItem>, n: usize) -> Vec<ResponseItem> {
+    if n == 0 || items.is_empty() {
+        return items;
+    }
+
+    // Walk backwards counting only `user` Message items, find cut index.
+    let mut count = 0usize;
+    let mut cut_index = 0usize;
+    for (idx, item) in items.iter().enumerate().rev() {
+        if let ResponseItem::Message { role, .. } = item
+            && role == "user"
+        {
+            count += 1;
+            if count == n {
+                // Cut everything from this user message to the end.
+                cut_index = idx;
+                break;
+            }
+        }
+    }
+    if count < n {
+        // If fewer than n messages exist, drop everything.
+        Vec::new()
+    } else {
+        items.into_iter().take(cut_index).collect()
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use codex_protocol::models::ContentItem;
+    use codex_protocol::models::ReasoningItemReasoningSummary;
+    use codex_protocol::models::ResponseItem;
+
+    fn user_msg(text: &str) -> ResponseItem {
+        ResponseItem::Message {
+            id: None,
+            role: "user".to_string(),
+            content: vec![ContentItem::OutputText {
+                text: text.to_string(),
+            }],
+        }
+    }
+    fn assistant_msg(text: &str) -> ResponseItem {
+        ResponseItem::Message {
+            id: None,
+            role: "assistant".to_string(),
+            content: vec![ContentItem::OutputText {
+                text: text.to_string(),
+            }],
+        }
+    }
+
+    #[test]
+    fn drops_from_last_user_only() {
+        let items = vec![
+            user_msg("u1"),
+            assistant_msg("a1"),
+            assistant_msg("a2"),
+            user_msg("u2"),
+            assistant_msg("a3"),
+            ResponseItem::Reasoning {
+                id: "r1".to_string(),
+                summary: vec![ReasoningItemReasoningSummary::SummaryText {
+                    text: "s".to_string(),
+                }],
+                content: None,
+                encrypted_content: None,
+            },
+            ResponseItem::FunctionCall {
+                id: None,
+                name: "tool".to_string(),
+                arguments: "{}".to_string(),
+                call_id: "c1".to_string(),
+            },
+            assistant_msg("a4"),
+        ];
+
+        let truncated = truncate_after_dropping_last_messages(items.clone(), 1);
+        assert_eq!(
+            truncated,
+            vec![items[0].clone(), items[1].clone(), items[2].clone()]
+        );
+
+        let truncated2 = truncate_after_dropping_last_messages(items, 2);
+        assert!(truncated2.is_empty());
+    }
 }

codex-rs/core/src/environment_context.rs

@@ -2,16 +2,16 @@ use serde::Deserialize;
 use serde::Serialize;
 use strum_macros::Display as DeriveDisplay;
 
-use crate::config_types::SandboxMode;
-use crate::models::ContentItem;
-use crate::models::ResponseItem;
 use crate::protocol::AskForApproval;
 use crate::protocol::SandboxPolicy;
-use std::fmt::Display;
+use crate::shell::Shell;
+use codex_protocol::config_types::SandboxMode;
+use codex_protocol::models::ContentItem;
+use codex_protocol::models::ResponseItem;
 use std::path::PathBuf;
 
 /// wraps environment context message in a tag for the model to parse more easily.
-pub(crate) const ENVIRONMENT_CONTEXT_START: &str = "<environment_context>\n";
+pub(crate) const ENVIRONMENT_CONTEXT_START: &str = "<environment_context>";
 pub(crate) const ENVIRONMENT_CONTEXT_END: &str = "</environment_context>";
 
 #[derive(Debug, Clone, Serialize, Deserialize, PartialEq, DeriveDisplay)]
@@ -24,52 +24,87 @@ pub enum NetworkAccess {
 #[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
 #[serde(rename = "environment_context", rename_all = "snake_case")]
 pub(crate) struct EnvironmentContext {
-    pub cwd: PathBuf,
-    pub approval_policy: AskForApproval,
-    pub sandbox_mode: SandboxMode,
-    pub network_access: NetworkAccess,
+    pub cwd: Option<PathBuf>,
+    pub approval_policy: Option<AskForApproval>,
+    pub sandbox_mode: Option<SandboxMode>,
+    pub network_access: Option<NetworkAccess>,
+    pub shell: Option<Shell>,
 }
 
 impl EnvironmentContext {
     pub fn new(
-        cwd: PathBuf,
-        approval_policy: AskForApproval,
-        sandbox_policy: SandboxPolicy,
+        cwd: Option<PathBuf>,
+        approval_policy: Option<AskForApproval>,
+        sandbox_policy: Option<SandboxPolicy>,
+        shell: Option<Shell>,
     ) -> Self {
         Self {
             cwd,
             approval_policy,
             sandbox_mode: match sandbox_policy {
-                SandboxPolicy::DangerFullAccess => SandboxMode::DangerFullAccess,
-                SandboxPolicy::ReadOnly => SandboxMode::ReadOnly,
-                SandboxPolicy::WorkspaceWrite { .. } => SandboxMode::WorkspaceWrite,
+                Some(SandboxPolicy::DangerFullAccess) => Some(SandboxMode::DangerFullAccess),
+                Some(SandboxPolicy::ReadOnly) => Some(SandboxMode::ReadOnly),
+                Some(SandboxPolicy::WorkspaceWrite { .. }) => Some(SandboxMode::WorkspaceWrite),
+                None => None,
             },
             network_access: match sandbox_policy {
-                SandboxPolicy::DangerFullAccess => NetworkAccess::Enabled,
-                SandboxPolicy::ReadOnly => NetworkAccess::Restricted,
-                SandboxPolicy::WorkspaceWrite { network_access, .. } => {
+                Some(SandboxPolicy::DangerFullAccess) => Some(NetworkAccess::Enabled),
+                Some(SandboxPolicy::ReadOnly) => Some(NetworkAccess::Restricted),
+                Some(SandboxPolicy::WorkspaceWrite { network_access, .. }) => {
                     if network_access {
-                        NetworkAccess::Enabled
+                        Some(NetworkAccess::Enabled)
                     } else {
-                        NetworkAccess::Restricted
+                        Some(NetworkAccess::Restricted)
                     }
                 }
+                None => None,
             },
+            shell,
         }
     }
 }
 
-impl Display for EnvironmentContext {
-    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
-        writeln!(
-            f,
-            "Current working directory: {}",
-            self.cwd.to_string_lossy()
-        )?;
-        writeln!(f, "Approval policy: {}", self.approval_policy)?;
-        writeln!(f, "Sandbox mode: {}", self.sandbox_mode)?;
-        writeln!(f, "Network access: {}", self.network_access)?;
-        Ok(())
+impl EnvironmentContext {
+    /// Serializes the environment context to XML. Libraries like `quick-xml`
+    /// require custom macros to handle Enums with newtypes, so we just do it
+    /// manually, to keep things simple. Output looks like:
+    ///
+    /// ```xml
+    /// <environment_context>
+    ///   <cwd>...</cwd>
+    ///   <approval_policy>...</approval_policy>
+    ///   <sandbox_mode>...</sandbox_mode>
+    ///   <network_access>...</network_access>
+    ///   <shell>...</shell>
+    /// </environment_context>
+    /// ```
+    pub fn serialize_to_xml(self) -> String {
+        let mut lines = vec![ENVIRONMENT_CONTEXT_START.to_string()];
+        if let Some(cwd) = self.cwd {
+            lines.push(format!("  <cwd>{}</cwd>", cwd.to_string_lossy()));
+        }
+        if let Some(approval_policy) = self.approval_policy {
+            lines.push(format!(
+                "  <approval_policy>{}</approval_policy>",
+                approval_policy
+            ));
+        }
+        if let Some(sandbox_mode) = self.sandbox_mode {
+            lines.push(format!("  <sandbox_mode>{}</sandbox_mode>", sandbox_mode));
+        }
+        if let Some(network_access) = self.network_access {
+            lines.push(format!(
+                "  <network_access>{}</network_access>",
+                network_access
+            ));
+        }
+        if let Some(shell) = self.shell
+            && let Some(shell_name) = shell.name()
+        {
+            lines.push(format!("  <shell>{}</shell>", shell_name));
+        }
+        lines.push(ENVIRONMENT_CONTEXT_END.to_string());
+        lines.join("\n")
     }
 }
 
@@ -79,7 +114,7 @@ impl From<EnvironmentContext> for ResponseItem {
             id: None,
             role: "user".to_string(),
             content: vec![ContentItem::InputText {
-                text: format!("{ENVIRONMENT_CONTEXT_START}{ec}{ENVIRONMENT_CONTEXT_END}"),
+                text: ec.serialize_to_xml(),
             }],
         }
     }

codex-rs/core/src/exec_command/exec_command_params.rs

@@ -0,0 +1,57 @@
+use serde::Deserialize;
+use serde::Serialize;
+
+use crate::exec_command::session_id::SessionId;
+
+#[derive(Debug, Clone, Deserialize)]
+pub struct ExecCommandParams {
+    pub(crate) cmd: String,
+
+    #[serde(default = "default_yield_time")]
+    pub(crate) yield_time_ms: u64,
+
+    #[serde(default = "max_output_tokens")]
+    pub(crate) max_output_tokens: u64,
+
+    #[serde(default = "default_shell")]
+    pub(crate) shell: String,
+
+    #[serde(default = "default_login")]
+    pub(crate) login: bool,
+}
+
+fn default_yield_time() -> u64 {
+    10_000
+}
+
+fn max_output_tokens() -> u64 {
+    10_000
+}
+
+fn default_login() -> bool {
+    true
+}
+
+fn default_shell() -> String {
+    "/bin/bash".to_string()
+}
+
+#[derive(Debug, Deserialize, Serialize)]
+pub struct WriteStdinParams {
+    pub(crate) session_id: SessionId,
+    pub(crate) chars: String,
+
+    #[serde(default = "write_stdin_default_yield_time_ms")]
+    pub(crate) yield_time_ms: u64,
+
+    #[serde(default = "write_stdin_default_max_output_tokens")]
+    pub(crate) max_output_tokens: u64,
+}
+
+fn write_stdin_default_yield_time_ms() -> u64 {
+    250
+}
+
+fn write_stdin_default_max_output_tokens() -> u64 {
+    10_000
+}

codex-rs/core/src/exec_command/exec_command_session.rs

@@ -0,0 +1,83 @@
+use std::sync::Mutex as StdMutex;
+
+use tokio::sync::broadcast;
+use tokio::sync::mpsc;
+use tokio::task::JoinHandle;
+
+#[derive(Debug)]
+pub(crate) struct ExecCommandSession {
+    /// Queue for writing bytes to the process stdin (PTY master write side).
+    writer_tx: mpsc::Sender<Vec<u8>>,
+    /// Broadcast stream of output chunks read from the PTY. New subscribers
+    /// receive only chunks emitted after they subscribe.
+    output_tx: broadcast::Sender<Vec<u8>>,
+
+    /// Child killer handle for termination on drop (can signal independently
+    /// of a thread blocked in `.wait()`).
+    killer: StdMutex<Option<Box<dyn portable_pty::ChildKiller + Send + Sync>>>,
+
+    /// JoinHandle for the blocking PTY reader task.
+    reader_handle: StdMutex<Option<JoinHandle<()>>>,
+
+    /// JoinHandle for the stdin writer task.
+    writer_handle: StdMutex<Option<JoinHandle<()>>>,
+
+    /// JoinHandle for the child wait task.
+    wait_handle: StdMutex<Option<JoinHandle<()>>>,
+}
+
+impl ExecCommandSession {
+    pub(crate) fn new(
+        writer_tx: mpsc::Sender<Vec<u8>>,
+        output_tx: broadcast::Sender<Vec<u8>>,
+        killer: Box<dyn portable_pty::ChildKiller + Send + Sync>,
+        reader_handle: JoinHandle<()>,
+        writer_handle: JoinHandle<()>,
+        wait_handle: JoinHandle<()>,
+    ) -> Self {
+        Self {
+            writer_tx,
+            output_tx,
+            killer: StdMutex::new(Some(killer)),
+            reader_handle: StdMutex::new(Some(reader_handle)),
+            writer_handle: StdMutex::new(Some(writer_handle)),
+            wait_handle: StdMutex::new(Some(wait_handle)),
+        }
+    }
+
+    pub(crate) fn writer_sender(&self) -> mpsc::Sender<Vec<u8>> {
+        self.writer_tx.clone()
+    }
+
+    pub(crate) fn output_receiver(&self) -> broadcast::Receiver<Vec<u8>> {
+        self.output_tx.subscribe()
+    }
+}
+
+impl Drop for ExecCommandSession {
+    fn drop(&mut self) {
+        // Best-effort: terminate child first so blocking tasks can complete.
+        if let Ok(mut killer_opt) = self.killer.lock()
+            && let Some(mut killer) = killer_opt.take()
+        {
+            let _ = killer.kill();
+        }
+
+        // Abort background tasks; they may already have exited after kill.
+        if let Ok(mut h) = self.reader_handle.lock()
+            && let Some(handle) = h.take()
+        {
+            handle.abort();
+        }
+        if let Ok(mut h) = self.writer_handle.lock()
+            && let Some(handle) = h.take()
+        {
+            handle.abort();
+        }
+        if let Ok(mut h) = self.wait_handle.lock()
+            && let Some(handle) = h.take()
+        {
+            handle.abort();
+        }
+    }
+}

codex-rs/core/src/exec_command/mod.rs

@@ -0,0 +1,14 @@
+mod exec_command_params;
+mod exec_command_session;
+mod responses_api;
+mod session_id;
+mod session_manager;
+
+pub use exec_command_params::ExecCommandParams;
+pub use exec_command_params::WriteStdinParams;
+pub use responses_api::EXEC_COMMAND_TOOL_NAME;
+pub use responses_api::WRITE_STDIN_TOOL_NAME;
+pub use responses_api::create_exec_command_tool_for_responses_api;
+pub use responses_api::create_write_stdin_tool_for_responses_api;
+pub use session_manager::SESSION_MANAGER;
+pub use session_manager::result_into_payload;

codex-rs/core/src/exec_command/responses_api.rs

@@ -0,0 +1,98 @@
+use std::collections::BTreeMap;
+
+use crate::openai_tools::JsonSchema;
+use crate::openai_tools::ResponsesApiTool;
+
+pub const EXEC_COMMAND_TOOL_NAME: &str = "exec_command";
+pub const WRITE_STDIN_TOOL_NAME: &str = "write_stdin";
+
+pub fn create_exec_command_tool_for_responses_api() -> ResponsesApiTool {
+    let mut properties = BTreeMap::<String, JsonSchema>::new();
+    properties.insert(
+        "cmd".to_string(),
+        JsonSchema::String {
+            description: Some("The shell command to execute.".to_string()),
+        },
+    );
+    properties.insert(
+        "yield_time_ms".to_string(),
+        JsonSchema::Number {
+            description: Some("The maximum time in milliseconds to wait for output.".to_string()),
+        },
+    );
+    properties.insert(
+        "max_output_tokens".to_string(),
+        JsonSchema::Number {
+            description: Some("The maximum number of tokens to output.".to_string()),
+        },
+    );
+    properties.insert(
+        "shell".to_string(),
+        JsonSchema::String {
+            description: Some("The shell to use. Defaults to \"/bin/bash\".".to_string()),
+        },
+    );
+    properties.insert(
+        "login".to_string(),
+        JsonSchema::Boolean {
+            description: Some(
+                "Whether to run the command as a login shell. Defaults to true.".to_string(),
+            ),
+        },
+    );
+
+    ResponsesApiTool {
+        name: EXEC_COMMAND_TOOL_NAME.to_owned(),
+        description: r#"Execute shell commands on the local machine with streaming output."#
+            .to_string(),
+        strict: false,
+        parameters: JsonSchema::Object {
+            properties,
+            required: Some(vec!["cmd".to_string()]),
+            additional_properties: Some(false),
+        },
+    }
+}
+
+pub fn create_write_stdin_tool_for_responses_api() -> ResponsesApiTool {
+    let mut properties = BTreeMap::<String, JsonSchema>::new();
+    properties.insert(
+        "session_id".to_string(),
+        JsonSchema::Number {
+            description: Some("The ID of the exec_command session.".to_string()),
+        },
+    );
+    properties.insert(
+        "chars".to_string(),
+        JsonSchema::String {
+            description: Some("The characters to write to stdin.".to_string()),
+        },
+    );
+    properties.insert(
+        "yield_time_ms".to_string(),
+        JsonSchema::Number {
+            description: Some(
+                "The maximum time in milliseconds to wait for output after writing.".to_string(),
+            ),
+        },
+    );
+    properties.insert(
+        "max_output_tokens".to_string(),
+        JsonSchema::Number {
+            description: Some("The maximum number of tokens to output.".to_string()),
+        },
+    );
+
+    ResponsesApiTool {
+        name: WRITE_STDIN_TOOL_NAME.to_owned(),
+        description: r#"Write characters to an exec session's stdin. Returns all stdout+stderr received within yield_time_ms.
+Can write control characters (\u0003 for Ctrl-C), or an empty string to just poll stdout+stderr."#
+            .to_string(),
+        strict: false,
+        parameters: JsonSchema::Object {
+            properties,
+            required: Some(vec!["session_id".to_string(), "chars".to_string()]),
+            additional_properties: Some(false),
+        },
+    }
+}

codex-rs/core/src/exec_command/session_id.rs

@@ -0,0 +1,5 @@
+use serde::Deserialize;
+use serde::Serialize;
+
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash, Serialize, Deserialize)]
+pub(crate) struct SessionId(pub u32);

codex-rs/core/src/exec_command/session_manager.rs

@@ -0,0 +1,677 @@
+use std::collections::HashMap;
+use std::io::ErrorKind;
+use std::io::Read;
+use std::sync::Arc;
+use std::sync::LazyLock;
+use std::sync::Mutex as StdMutex;
+use std::sync::atomic::AtomicU32;
+
+use portable_pty::CommandBuilder;
+use portable_pty::PtySize;
+use portable_pty::native_pty_system;
+use tokio::sync::Mutex;
+use tokio::sync::mpsc;
+use tokio::sync::oneshot;
+use tokio::time::Duration;
+use tokio::time::Instant;
+use tokio::time::timeout;
+
+use crate::exec_command::exec_command_params::ExecCommandParams;
+use crate::exec_command::exec_command_params::WriteStdinParams;
+use crate::exec_command::exec_command_session::ExecCommandSession;
+use crate::exec_command::session_id::SessionId;
+use codex_protocol::models::FunctionCallOutputPayload;
+
+pub static SESSION_MANAGER: LazyLock<SessionManager> = LazyLock::new(SessionManager::default);
+
+#[derive(Debug, Default)]
+pub struct SessionManager {
+    next_session_id: AtomicU32,
+    sessions: Mutex<HashMap<SessionId, ExecCommandSession>>,
+}
+
+#[derive(Debug)]
+pub struct ExecCommandOutput {
+    wall_time: Duration,
+    exit_status: ExitStatus,
+    original_token_count: Option<u64>,
+    output: String,
+}
+
+impl ExecCommandOutput {
+    fn to_text_output(&self) -> String {
+        let wall_time_secs = self.wall_time.as_secs_f32();
+        let termination_status = match self.exit_status {
+            ExitStatus::Exited(code) => format!("Process exited with code {code}"),
+            ExitStatus::Ongoing(session_id) => {
+                format!("Process running with session ID {}", session_id.0)
+            }
+        };
+        let truncation_status = match self.original_token_count {
+            Some(tokens) => {
+                format!("\nWarning: truncated output (original token count: {tokens})")
+            }
+            None => "".to_string(),
+        };
+        format!(
+            r#"Wall time: {wall_time_secs:.3} seconds
+{termination_status}{truncation_status}
+Output:
+{output}"#,
+            output = self.output
+        )
+    }
+}
+
+#[derive(Debug)]
+pub enum ExitStatus {
+    Exited(i32),
+    Ongoing(SessionId),
+}
+
+pub fn result_into_payload(result: Result<ExecCommandOutput, String>) -> FunctionCallOutputPayload {
+    match result {
+        Ok(output) => FunctionCallOutputPayload {
+            content: output.to_text_output(),
+            success: Some(true),
+        },
+        Err(err) => FunctionCallOutputPayload {
+            content: err,
+            success: Some(false),
+        },
+    }
+}
+
+impl SessionManager {
+    /// Processes the request and is required to send a response via `outgoing`.
+    pub async fn handle_exec_command_request(
+        &self,
+        params: ExecCommandParams,
+    ) -> Result<ExecCommandOutput, String> {
+        // Allocate a session id.
+        let session_id = SessionId(
+            self.next_session_id
+                .fetch_add(1, std::sync::atomic::Ordering::SeqCst),
+        );
+
+        let (session, mut exit_rx) =
+            create_exec_command_session(params.clone())
+                .await
+                .map_err(|err| {
+                    format!(
+                        "failed to create exec command session for session id {}: {err}",
+                        session_id.0
+                    )
+                })?;
+
+        // Insert into session map.
+        let mut output_rx = session.output_receiver();
+        self.sessions.lock().await.insert(session_id, session);
+
+        // Collect output until either timeout expires or process exits.
+        // Do not cap during collection; truncate at the end if needed.
+        // Use a modest initial capacity to avoid large preallocation.
+        let cap_bytes_u64 = params.max_output_tokens.saturating_mul(4);
+        let cap_bytes: usize = cap_bytes_u64.min(usize::MAX as u64) as usize;
+        let mut collected: Vec<u8> = Vec::with_capacity(4096);
+
+        let start_time = Instant::now();
+        let deadline = start_time + Duration::from_millis(params.yield_time_ms);
+        let mut exit_code: Option<i32> = None;
+
+        loop {
+            if Instant::now() >= deadline {
+                break;
+            }
+            let remaining = deadline.saturating_duration_since(Instant::now());
+            tokio::select! {
+                biased;
+                exit = &mut exit_rx => {
+                    exit_code = exit.ok();
+                    // Small grace period to pull remaining buffered output
+                    let grace_deadline = Instant::now() + Duration::from_millis(25);
+                    while Instant::now() < grace_deadline {
+                        match timeout(Duration::from_millis(1), output_rx.recv()).await {
+                            Ok(Ok(chunk)) => {
+                                collected.extend_from_slice(&chunk);
+                            }
+                            Ok(Err(tokio::sync::broadcast::error::RecvError::Lagged(_))) => {
+                                // Skip missed messages; keep trying within grace period.
+                                continue;
+                            }
+                            Ok(Err(tokio::sync::broadcast::error::RecvError::Closed)) => break,
+                            Err(_) => break,
+                        }
+                    }
+                    break;
+                }
+                chunk = timeout(remaining, output_rx.recv()) => {
+                    match chunk {
+                        Ok(Ok(chunk)) => {
+                            collected.extend_from_slice(&chunk);
+                        }
+                        Ok(Err(tokio::sync::broadcast::error::RecvError::Lagged(_))) => {
+                            // Skip missed messages; continue collecting fresh output.
+                        }
+                        Ok(Err(tokio::sync::broadcast::error::RecvError::Closed)) => { break; }
+                        Err(_) => { break; }
+                    }
+                }
+            }
+        }
+
+        let output = String::from_utf8_lossy(&collected).to_string();
+
+        let exit_status = if let Some(code) = exit_code {
+            ExitStatus::Exited(code)
+        } else {
+            ExitStatus::Ongoing(session_id)
+        };
+
+        // If output exceeds cap, truncate the middle and record original token estimate.
+        let (output, original_token_count) = truncate_middle(&output, cap_bytes);
+        Ok(ExecCommandOutput {
+            wall_time: Instant::now().duration_since(start_time),
+            exit_status,
+            original_token_count,
+            output,
+        })
+    }
+
+    /// Write characters to a session's stdin and collect combined output for up to `yield_time_ms`.
+    pub async fn handle_write_stdin_request(
+        &self,
+        params: WriteStdinParams,
+    ) -> Result<ExecCommandOutput, String> {
+        let WriteStdinParams {
+            session_id,
+            chars,
+            yield_time_ms,
+            max_output_tokens,
+        } = params;
+
+        // Grab handles without holding the sessions lock across await points.
+        let (writer_tx, mut output_rx) = {
+            let sessions = self.sessions.lock().await;
+            match sessions.get(&session_id) {
+                Some(session) => (session.writer_sender(), session.output_receiver()),
+                None => {
+                    return Err(format!("unknown session id {}", session_id.0));
+                }
+            }
+        };
+
+        // Write stdin if provided.
+        if !chars.is_empty() && writer_tx.send(chars.into_bytes()).await.is_err() {
+            return Err("failed to write to stdin".to_string());
+        }
+
+        // Collect output up to yield_time_ms, truncating to max_output_tokens bytes.
+        let mut collected: Vec<u8> = Vec::with_capacity(4096);
+        let start_time = Instant::now();
+        let deadline = start_time + Duration::from_millis(yield_time_ms);
+        loop {
+            let now = Instant::now();
+            if now >= deadline {
+                break;
+            }
+            let remaining = deadline - now;
+            match timeout(remaining, output_rx.recv()).await {
+                Ok(Ok(chunk)) => {
+                    // Collect all output within the time budget; truncate at the end.
+                    collected.extend_from_slice(&chunk);
+                }
+                Ok(Err(tokio::sync::broadcast::error::RecvError::Lagged(_))) => {
+                    // Skip missed messages; continue collecting fresh output.
+                }
+                Ok(Err(tokio::sync::broadcast::error::RecvError::Closed)) => break,
+                Err(_) => break, // timeout
+            }
+        }
+
+        // Return structured output, truncating middle if over cap.
+        let output = String::from_utf8_lossy(&collected).to_string();
+        let cap_bytes_u64 = max_output_tokens.saturating_mul(4);
+        let cap_bytes: usize = cap_bytes_u64.min(usize::MAX as u64) as usize;
+        let (output, original_token_count) = truncate_middle(&output, cap_bytes);
+        Ok(ExecCommandOutput {
+            wall_time: Instant::now().duration_since(start_time),
+            exit_status: ExitStatus::Ongoing(session_id),
+            original_token_count,
+            output,
+        })
+    }
+}
+
+/// Spawn PTY and child process per spawn_exec_command_session logic.
+async fn create_exec_command_session(
+    params: ExecCommandParams,
+) -> anyhow::Result<(ExecCommandSession, oneshot::Receiver<i32>)> {
+    let ExecCommandParams {
+        cmd,
+        yield_time_ms: _,
+        max_output_tokens: _,
+        shell,
+        login,
+    } = params;
+
+    // Use the native pty implementation for the system
+    let pty_system = native_pty_system();
+
+    // Create a new pty
+    let pair = pty_system.openpty(PtySize {
+        rows: 24,
+        cols: 80,
+        pixel_width: 0,
+        pixel_height: 0,
+    })?;
+
+    // Spawn a shell into the pty
+    let mut command_builder = CommandBuilder::new(shell);
+    let shell_mode_opt = if login { "-lc" } else { "-c" };
+    command_builder.arg(shell_mode_opt);
+    command_builder.arg(cmd);
+
+    let mut child = pair.slave.spawn_command(command_builder)?;
+    // Obtain a killer that can signal the process independently of `.wait()`.
+    let killer = child.clone_killer();
+
+    // Channel to forward write requests to the PTY writer.
+    let (writer_tx, mut writer_rx) = mpsc::channel::<Vec<u8>>(128);
+    // Broadcast for streaming PTY output to readers: subscribers receive from subscription time.
+    let (output_tx, _) = tokio::sync::broadcast::channel::<Vec<u8>>(256);
+
+    // Reader task: drain PTY and forward chunks to output channel.
+    let mut reader = pair.master.try_clone_reader()?;
+    let output_tx_clone = output_tx.clone();
+    let reader_handle = tokio::task::spawn_blocking(move || {
+        let mut buf = [0u8; 8192];
+        loop {
+            match reader.read(&mut buf) {
+                Ok(0) => break, // EOF
+                Ok(n) => {
+                    // Forward to broadcast; best-effort if there are subscribers.
+                    let _ = output_tx_clone.send(buf[..n].to_vec());
+                }
+                Err(ref e) if e.kind() == ErrorKind::Interrupted => {
+                    // Retry on EINTR
+                    continue;
+                }
+                Err(ref e) if e.kind() == ErrorKind::WouldBlock => {
+                    // We're in a blocking thread; back off briefly and retry.
+                    std::thread::sleep(Duration::from_millis(5));
+                    continue;
+                }
+                Err(_) => break,
+            }
+        }
+    });
+
+    // Writer task: apply stdin writes to the PTY writer.
+    let writer = pair.master.take_writer()?;
+    let writer = Arc::new(StdMutex::new(writer));
+    let writer_handle = tokio::spawn({
+        let writer = writer.clone();
+        async move {
+            while let Some(bytes) = writer_rx.recv().await {
+                let writer = writer.clone();
+                // Perform blocking write on a blocking thread.
+                let _ = tokio::task::spawn_blocking(move || {
+                    if let Ok(mut guard) = writer.lock() {
+                        use std::io::Write;
+                        let _ = guard.write_all(&bytes);
+                        let _ = guard.flush();
+                    }
+                })
+                .await;
+            }
+        }
+    });
+
+    // Keep the child alive until it exits, then signal exit code.
+    let (exit_tx, exit_rx) = oneshot::channel::<i32>();
+    let wait_handle = tokio::task::spawn_blocking(move || {
+        let code = match child.wait() {
+            Ok(status) => status.exit_code() as i32,
+            Err(_) => -1,
+        };
+        let _ = exit_tx.send(code);
+    });
+
+    // Create and store the session with channels.
+    let session = ExecCommandSession::new(
+        writer_tx,
+        output_tx,
+        killer,
+        reader_handle,
+        writer_handle,
+        wait_handle,
+    );
+    Ok((session, exit_rx))
+}
+
+/// Truncate the middle of a UTF-8 string to at most `max_bytes` bytes,
+/// preserving the beginning and the end. Returns the possibly truncated
+/// string and `Some(original_token_count)` (estimated at 4 bytes/token)
+/// if truncation occurred; otherwise returns the original string and `None`.
+fn truncate_middle(s: &str, max_bytes: usize) -> (String, Option<u64>) {
+    // No truncation needed
+    if s.len() <= max_bytes {
+        return (s.to_string(), None);
+    }
+    let est_tokens = (s.len() as u64).div_ceil(4);
+    if max_bytes == 0 {
+        // Cannot keep any content; still return a full marker (never truncated).
+        return (
+            format!("…{} tokens truncated…", est_tokens),
+            Some(est_tokens),
+        );
+    }
+
+    // Helper to truncate a string to a given byte length on a char boundary.
+    fn truncate_on_boundary(input: &str, max_len: usize) -> &str {
+        if input.len() <= max_len {
+            return input;
+        }
+        let mut end = max_len;
+        while end > 0 && !input.is_char_boundary(end) {
+            end -= 1;
+        }
+        &input[..end]
+    }
+
+    // Given a left/right budget, prefer newline boundaries; otherwise fall back
+    // to UTF-8 char boundaries.
+    fn pick_prefix_end(s: &str, left_budget: usize) -> usize {
+        if let Some(head) = s.get(..left_budget)
+            && let Some(i) = head.rfind('\n')
+        {
+            return i + 1; // keep the newline so suffix starts on a fresh line
+        }
+        truncate_on_boundary(s, left_budget).len()
+    }
+
+    fn pick_suffix_start(s: &str, right_budget: usize) -> usize {
+        let start_tail = s.len().saturating_sub(right_budget);
+        if let Some(tail) = s.get(start_tail..)
+            && let Some(i) = tail.find('\n')
+        {
+            return start_tail + i + 1; // start after newline
+        }
+        // Fall back to a char boundary at or after start_tail.
+        let mut idx = start_tail.min(s.len());
+        while idx < s.len() && !s.is_char_boundary(idx) {
+            idx += 1;
+        }
+        idx
+    }
+
+    // Refine marker length and budgets until stable. Marker is never truncated.
+    let mut guess_tokens = est_tokens; // worst-case: everything truncated
+    for _ in 0..4 {
+        let marker = format!("…{} tokens truncated…", guess_tokens);
+        let marker_len = marker.len();
+        let keep_budget = max_bytes.saturating_sub(marker_len);
+        if keep_budget == 0 {
+            // No room for any content within the cap; return a full, untruncated marker
+            // that reflects the entire truncated content.
+            return (
+                format!("…{} tokens truncated…", est_tokens),
+                Some(est_tokens),
+            );
+        }
+
+        let left_budget = keep_budget / 2;
+        let right_budget = keep_budget - left_budget;
+        let prefix_end = pick_prefix_end(s, left_budget);
+        let mut suffix_start = pick_suffix_start(s, right_budget);
+        if suffix_start < prefix_end {
+            suffix_start = prefix_end;
+        }
+        let kept_content_bytes = prefix_end + (s.len() - suffix_start);
+        let truncated_content_bytes = s.len().saturating_sub(kept_content_bytes);
+        let new_tokens = (truncated_content_bytes as u64).div_ceil(4);
+        if new_tokens == guess_tokens {
+            let mut out = String::with_capacity(marker_len + kept_content_bytes + 1);
+            out.push_str(&s[..prefix_end]);
+            out.push_str(&marker);
+            // Place marker on its own line for symmetry when we keep line boundaries.
+            out.push('\n');
+            out.push_str(&s[suffix_start..]);
+            return (out, Some(est_tokens));
+        }
+        guess_tokens = new_tokens;
+    }
+
+    // Fallback: use last guess to build output.
+    let marker = format!("…{} tokens truncated…", guess_tokens);
+    let marker_len = marker.len();
+    let keep_budget = max_bytes.saturating_sub(marker_len);
+    if keep_budget == 0 {
+        return (
+            format!("…{} tokens truncated…", est_tokens),
+            Some(est_tokens),
+        );
+    }
+    let left_budget = keep_budget / 2;
+    let right_budget = keep_budget - left_budget;
+    let prefix_end = pick_prefix_end(s, left_budget);
+    let suffix_start = pick_suffix_start(s, right_budget);
+    let mut out = String::with_capacity(marker_len + prefix_end + (s.len() - suffix_start) + 1);
+    out.push_str(&s[..prefix_end]);
+    out.push_str(&marker);
+    out.push('\n');
+    out.push_str(&s[suffix_start..]);
+    (out, Some(est_tokens))
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+    use crate::exec_command::session_id::SessionId;
+
+    /// Test that verifies that [`SessionManager::handle_exec_command_request()`]
+    /// and [`SessionManager::handle_write_stdin_request()`] work as expected
+    /// in the presence of a process that never terminates (but produces
+    /// output continuously).
+    #[cfg(unix)]
+    #[allow(clippy::print_stderr)]
+    #[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+    async fn session_manager_streams_and_truncates_from_now() {
+        use crate::exec_command::exec_command_params::ExecCommandParams;
+        use crate::exec_command::exec_command_params::WriteStdinParams;
+        use tokio::time::sleep;
+
+        let session_manager = SessionManager::default();
+        // Long-running loop that prints an increasing counter every ~100ms.
+        // Use Python for a portable, reliable sleep across shells/PTYs.
+        let cmd = r#"python3 - <<'PY'
+import sys, time
+count = 0
+while True:
+    print(count)
+    sys.stdout.flush()
+    count += 100
+    time.sleep(0.1)
+PY"#
+        .to_string();
+
+        // Start the session and collect ~3s of output.
+        let params = ExecCommandParams {
+            cmd,
+            yield_time_ms: 3_000,
+            max_output_tokens: 1_000, // large enough to avoid truncation here
+            shell: "/bin/bash".to_string(),
+            login: false,
+        };
+        let initial_output = match session_manager
+            .handle_exec_command_request(params.clone())
+            .await
+        {
+            Ok(v) => v,
+            Err(e) => {
+                // PTY may be restricted in some sandboxes; skip in that case.
+                if e.contains("openpty") || e.contains("Operation not permitted") {
+                    eprintln!("skipping test due to restricted PTY: {e}");
+                    return;
+                }
+                panic!("exec request failed unexpectedly: {e}");
+            }
+        };
+        eprintln!("initial output: {initial_output:?}");
+
+        // Should be ongoing (we launched a never-ending loop).
+        let session_id = match initial_output.exit_status {
+            ExitStatus::Ongoing(id) => id,
+            _ => panic!("expected ongoing session"),
+        };
+
+        // Parse the numeric lines and get the max observed value in the first window.
+        let first_nums = extract_monotonic_numbers(&initial_output.output);
+        assert!(
+            !first_nums.is_empty(),
+            "expected some output from first window"
+        );
+        let first_max = *first_nums.iter().max().unwrap();
+
+        // Wait ~4s so counters progress while we're not reading.
+        sleep(Duration::from_millis(4_000)).await;
+
+        // Now read ~3s of output "from now" only.
+        // Use a small token cap so truncation occurs and we test middle truncation.
+        let write_params = WriteStdinParams {
+            session_id,
+            chars: String::new(),
+            yield_time_ms: 3_000,
+            max_output_tokens: 16, // 16 tokens ~= 64 bytes -> likely truncation
+        };
+        let second = session_manager
+            .handle_write_stdin_request(write_params)
+            .await
+            .expect("write stdin should succeed");
+
+        // Verify truncation metadata and size bound (cap is tokens*4 bytes).
+        assert!(second.original_token_count.is_some());
+        let cap_bytes = (16u64 * 4) as usize;
+        assert!(second.output.len() <= cap_bytes);
+        // New middle marker should be present.
+        assert!(
+            second.output.contains("tokens truncated") && second.output.contains('…'),
+            "expected truncation marker in output, got: {}",
+            second.output
+        );
+
+        // Minimal freshness check: the earliest number we see in the second window
+        // should be significantly larger than the last from the first window.
+        let second_nums = extract_monotonic_numbers(&second.output);
+        assert!(
+            !second_nums.is_empty(),
+            "expected some numeric output from second window"
+        );
+        let second_min = *second_nums.iter().min().unwrap();
+
+        // We slept 4 seconds (~40 ticks at 100ms/tick, each +100), so expect
+        // an increase of roughly 4000 or more. Allow a generous margin.
+        assert!(
+            second_min >= first_max + 2000,
+            "second_min={second_min} first_max={first_max}",
+        );
+    }
+
+    #[cfg(unix)]
+    fn extract_monotonic_numbers(s: &str) -> Vec<i64> {
+        s.lines()
+            .filter_map(|line| {
+                if !line.is_empty()
+                    && line.chars().all(|c| c.is_ascii_digit())
+                    && let Ok(n) = line.parse::<i64>()
+                {
+                    // Our generator increments by 100; ignore spurious fragments.
+                    if n % 100 == 0 {
+                        return Some(n);
+                    }
+                }
+                None
+            })
+            .collect()
+    }
+
+    #[test]
+    fn to_text_output_exited_no_truncation() {
+        let out = ExecCommandOutput {
+            wall_time: Duration::from_millis(1234),
+            exit_status: ExitStatus::Exited(0),
+            original_token_count: None,
+            output: "hello".to_string(),
+        };
+        let text = out.to_text_output();
+        let expected = r#"Wall time: 1.234 seconds
+Process exited with code 0
+Output:
+hello"#;
+        assert_eq!(expected, text);
+    }
+
+    #[test]
+    fn to_text_output_ongoing_with_truncation() {
+        let out = ExecCommandOutput {
+            wall_time: Duration::from_millis(500),
+            exit_status: ExitStatus::Ongoing(SessionId(42)),
+            original_token_count: Some(1000),
+            output: "abc".to_string(),
+        };
+        let text = out.to_text_output();
+        let expected = r#"Wall time: 0.500 seconds
+Process running with session ID 42
+Warning: truncated output (original token count: 1000)
+Output:
+abc"#;
+        assert_eq!(expected, text);
+    }
+
+    #[test]
+    fn truncate_middle_no_newlines_fallback() {
+        // A long string with no newlines that exceeds the cap.
+        let s = "abcdefghijklmnopqrstuvwxyz0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+        let max_bytes = 16; // force truncation
+        let (out, original) = truncate_middle(s, max_bytes);
+        // For very small caps, we return the full, untruncated marker,
+        // even if it exceeds the cap.
+        assert_eq!(out, "…16 tokens truncated…");
+        // Original string length is 62 bytes => ceil(62/4) = 16 tokens.
+        assert_eq!(original, Some(16));
+    }
+
+    #[test]
+    fn truncate_middle_prefers_newline_boundaries() {
+        // Build a multi-line string of 20 numbered lines (each "NNN\n").
+        let mut s = String::new();
+        for i in 1..=20 {
+            s.push_str(&format!("{i:03}\n"));
+        }
+        // Total length: 20 lines * 4 bytes per line = 80 bytes.
+        assert_eq!(s.len(), 80);
+
+        // Choose a cap that forces truncation while leaving room for
+        // a few lines on each side after accounting for the marker.
+        let max_bytes = 64;
+        // Expect exact output: first 4 lines, marker, last 4 lines, and correct token estimate (80/4 = 20).
+        assert_eq!(
+            truncate_middle(&s, max_bytes),
+            (
+                r#"001
+002
+003
+004
+…12 tokens truncated…
+017
+018
+019
+020
+"#
+                .to_string(),
+                Some(20)
+            )
+        );
+    }
+}

codex-rs/core/src/git_info.rs

@@ -1,11 +1,17 @@
+use std::collections::HashSet;
 use std::path::Path;
+use std::path::PathBuf;
 
+use codex_protocol::mcp_protocol::GitSha;
+use futures::future::join_all;
 use serde::Deserialize;
 use serde::Serialize;
 use tokio::process::Command;
 use tokio::time::Duration as TokioDuration;
 use tokio::time::timeout;
 
+use crate::util::is_inside_git_repo;
+
 /// Timeout for git commands to prevent freezing on large repositories
 const GIT_COMMAND_TIMEOUT: TokioDuration = TokioDuration::from_secs(5);
 
@@ -22,6 +28,12 @@ pub struct GitInfo {
     pub repository_url: Option<String>,
 }
 
+#[derive(Serialize, Deserialize, Clone, Debug)]
+pub struct GitDiffToRemote {
+    pub sha: GitSha,
+    pub diff: String,
+}
+
 /// Collect git repository information from the given working directory using command-line git.
 /// Returns None if no git repository is found or if git operations fail.
 /// Uses timeouts to prevent freezing on large repositories.
@@ -51,38 +63,52 @@ pub async fn collect_git_info(cwd: &Path) -> Option<GitInfo> {
     };
 
     // Process commit hash
-    if let Some(output) = commit_result {
-        if output.status.success() {
-            if let Ok(hash) = String::from_utf8(output.stdout) {
-                git_info.commit_hash = Some(hash.trim().to_string());
-            }
-        }
+    if let Some(output) = commit_result
+        && output.status.success()
+        && let Ok(hash) = String::from_utf8(output.stdout)
+    {
+        git_info.commit_hash = Some(hash.trim().to_string());
     }
 
     // Process branch name
-    if let Some(output) = branch_result {
-        if output.status.success() {
-            if let Ok(branch) = String::from_utf8(output.stdout) {
-                let branch = branch.trim();
-                if branch != "HEAD" {
-                    git_info.branch = Some(branch.to_string());
-                }
-            }
+    if let Some(output) = branch_result
+        && output.status.success()
+        && let Ok(branch) = String::from_utf8(output.stdout)
+    {
+        let branch = branch.trim();
+        if branch != "HEAD" {
+            git_info.branch = Some(branch.to_string());
         }
     }
 
     // Process repository URL
-    if let Some(output) = url_result {
-        if output.status.success() {
-            if let Ok(url) = String::from_utf8(output.stdout) {
-                git_info.repository_url = Some(url.trim().to_string());
-            }
-        }
+    if let Some(output) = url_result
+        && output.status.success()
+        && let Ok(url) = String::from_utf8(output.stdout)
+    {
+        git_info.repository_url = Some(url.trim().to_string());
     }
 
     Some(git_info)
 }
 
+/// Returns the closest git sha to HEAD that is on a remote as well as the diff to that sha.
+pub async fn git_diff_to_remote(cwd: &Path) -> Option<GitDiffToRemote> {
+    if !is_inside_git_repo(cwd) {
+        return None;
+    }
+
+    let remotes = get_git_remotes(cwd).await?;
+    let branches = branch_ancestry(cwd).await?;
+    let base_sha = find_closest_sha(cwd, &branches, &remotes).await?;
+    let diff = diff_against_sha(cwd, &base_sha).await?;
+
+    Some(GitDiffToRemote {
+        sha: base_sha,
+        diff,
+    })
+}
+
 /// Run a git command with a timeout to prevent blocking on large repositories
 async fn run_git_command_with_timeout(args: &[&str], cwd: &Path) -> Option<std::process::Output> {
     let result = timeout(
@@ -97,6 +123,341 @@ async fn run_git_command_with_timeout(args: &[&str], cwd: &Path) -> Option<std::
     }
 }
 
+async fn get_git_remotes(cwd: &Path) -> Option<Vec<String>> {
+    let output = run_git_command_with_timeout(&["remote"], cwd).await?;
+    if !output.status.success() {
+        return None;
+    }
+    let mut remotes: Vec<String> = String::from_utf8(output.stdout)
+        .ok()?
+        .lines()
+        .map(|s| s.to_string())
+        .collect();
+    if let Some(pos) = remotes.iter().position(|r| r == "origin") {
+        let origin = remotes.remove(pos);
+        remotes.insert(0, origin);
+    }
+    Some(remotes)
+}
+
+/// Attempt to determine the repository's default branch name.
+///
+/// Preference order:
+/// 1) The symbolic ref at `refs/remotes/<remote>/HEAD` for the first remote (origin prioritized)
+/// 2) `git remote show <remote>` parsed for "HEAD branch: <name>"
+/// 3) Local fallback to existing `main` or `master` if present
+async fn get_default_branch(cwd: &Path) -> Option<String> {
+    // Prefer the first remote (with origin prioritized)
+    let remotes = get_git_remotes(cwd).await.unwrap_or_default();
+    for remote in remotes {
+        // Try symbolic-ref, which returns something like: refs/remotes/origin/main
+        if let Some(symref_output) = run_git_command_with_timeout(
+            &[
+                "symbolic-ref",
+                "--quiet",
+                &format!("refs/remotes/{remote}/HEAD"),
+            ],
+            cwd,
+        )
+        .await
+            && symref_output.status.success()
+            && let Ok(sym) = String::from_utf8(symref_output.stdout)
+        {
+            let trimmed = sym.trim();
+            if let Some((_, name)) = trimmed.rsplit_once('/') {
+                return Some(name.to_string());
+            }
+        }
+
+        // Fall back to parsing `git remote show <remote>` output
+        if let Some(show_output) =
+            run_git_command_with_timeout(&["remote", "show", &remote], cwd).await
+            && show_output.status.success()
+            && let Ok(text) = String::from_utf8(show_output.stdout)
+        {
+            for line in text.lines() {
+                let line = line.trim();
+                if let Some(rest) = line.strip_prefix("HEAD branch:") {
+                    let name = rest.trim();
+                    if !name.is_empty() {
+                        return Some(name.to_string());
+                    }
+                }
+            }
+        }
+    }
+
+    // No remote-derived default; try common local defaults if they exist
+    for candidate in ["main", "master"] {
+        if let Some(verify) = run_git_command_with_timeout(
+            &[
+                "rev-parse",
+                "--verify",
+                "--quiet",
+                &format!("refs/heads/{candidate}"),
+            ],
+            cwd,
+        )
+        .await
+            && verify.status.success()
+        {
+            return Some(candidate.to_string());
+        }
+    }
+
+    None
+}
+
+/// Build an ancestry of branches starting at the current branch and ending at the
+/// repository's default branch (if determinable)..
+async fn branch_ancestry(cwd: &Path) -> Option<Vec<String>> {
+    // Discover current branch (ignore detached HEAD by treating it as None)
+    let current_branch = run_git_command_with_timeout(&["rev-parse", "--abbrev-ref", "HEAD"], cwd)
+        .await
+        .and_then(|o| {
+            if o.status.success() {
+                String::from_utf8(o.stdout).ok()
+            } else {
+                None
+            }
+        })
+        .map(|s| s.trim().to_string())
+        .filter(|s| s != "HEAD");
+
+    // Discover default branch
+    let default_branch = get_default_branch(cwd).await;
+
+    let mut ancestry: Vec<String> = Vec::new();
+    let mut seen: HashSet<String> = HashSet::new();
+    if let Some(cb) = current_branch.clone() {
+        seen.insert(cb.clone());
+        ancestry.push(cb);
+    }
+    if let Some(db) = default_branch
+        && !seen.contains(&db)
+    {
+        seen.insert(db.clone());
+        ancestry.push(db);
+    }
+
+    // Expand candidates: include any remote branches that already contain HEAD.
+    // This addresses cases where we're on a new local-only branch forked from a
+    // remote branch that isn't the repository default. We prioritize remotes in
+    // the order returned by get_git_remotes (origin first).
+    let remotes = get_git_remotes(cwd).await.unwrap_or_default();
+    for remote in remotes {
+        if let Some(output) = run_git_command_with_timeout(
+            &[
+                "for-each-ref",
+                "--format=%(refname:short)",
+                "--contains=HEAD",
+                &format!("refs/remotes/{remote}"),
+            ],
+            cwd,
+        )
+        .await
+            && output.status.success()
+            && let Ok(text) = String::from_utf8(output.stdout)
+        {
+            for line in text.lines() {
+                let short = line.trim();
+                // Expect format like: "origin/feature"; extract the branch path after "remote/"
+                if let Some(stripped) = short.strip_prefix(&format!("{remote}/"))
+                    && !stripped.is_empty()
+                    && !seen.contains(stripped)
+                {
+                    seen.insert(stripped.to_string());
+                    ancestry.push(stripped.to_string());
+                }
+            }
+        }
+    }
+
+    // Ensure we return Some vector, even if empty, to allow caller logic to proceed
+    Some(ancestry)
+}
+
+// Helper for a single branch: return the remote SHA if present on any remote
+// and the distance (commits ahead of HEAD) for that branch. The first item is
+// None if the branch is not present on any remote. Returns None if distance
+// could not be computed due to git errors/timeouts.
+async fn branch_remote_and_distance(
+    cwd: &Path,
+    branch: &str,
+    remotes: &[String],
+) -> Option<(Option<GitSha>, usize)> {
+    // Try to find the first remote ref that exists for this branch (origin prioritized by caller).
+    let mut found_remote_sha: Option<GitSha> = None;
+    let mut found_remote_ref: Option<String> = None;
+    for remote in remotes {
+        let remote_ref = format!("refs/remotes/{remote}/{branch}");
+        let Some(verify_output) =
+            run_git_command_with_timeout(&["rev-parse", "--verify", "--quiet", &remote_ref], cwd)
+                .await
+        else {
+            // Mirror previous behavior: if the verify call times out/fails at the process level,
+            // treat the entire branch as unusable.
+            return None;
+        };
+        if !verify_output.status.success() {
+            continue;
+        }
+        let Ok(sha) = String::from_utf8(verify_output.stdout) else {
+            // Mirror previous behavior and skip the entire branch on parse failure.
+            return None;
+        };
+        found_remote_sha = Some(GitSha::new(sha.trim()));
+        found_remote_ref = Some(remote_ref);
+        break;
+    }
+
+    // Compute distance as the number of commits HEAD is ahead of the branch.
+    // Prefer local branch name if it exists; otherwise fall back to the remote ref (if any).
+    let count_output = if let Some(local_count) =
+        run_git_command_with_timeout(&["rev-list", "--count", &format!("{branch}..HEAD")], cwd)
+            .await
+    {
+        if local_count.status.success() {
+            local_count
+        } else if let Some(remote_ref) = &found_remote_ref {
+            match run_git_command_with_timeout(
+                &["rev-list", "--count", &format!("{remote_ref}..HEAD")],
+                cwd,
+            )
+            .await
+            {
+                Some(remote_count) => remote_count,
+                None => return None,
+            }
+        } else {
+            return None;
+        }
+    } else if let Some(remote_ref) = &found_remote_ref {
+        match run_git_command_with_timeout(
+            &["rev-list", "--count", &format!("{remote_ref}..HEAD")],
+            cwd,
+        )
+        .await
+        {
+            Some(remote_count) => remote_count,
+            None => return None,
+        }
+    } else {
+        return None;
+    };
+
+    if !count_output.status.success() {
+        return None;
+    }
+    let Ok(distance_str) = String::from_utf8(count_output.stdout) else {
+        return None;
+    };
+    let Ok(distance) = distance_str.trim().parse::<usize>() else {
+        return None;
+    };
+
+    Some((found_remote_sha, distance))
+}
+
+// Finds the closest sha that exist on any of branches and also exists on any of the remotes.
+async fn find_closest_sha(cwd: &Path, branches: &[String], remotes: &[String]) -> Option<GitSha> {
+    // A sha and how many commits away from HEAD it is.
+    let mut closest_sha: Option<(GitSha, usize)> = None;
+    for branch in branches {
+        let Some((maybe_remote_sha, distance)) =
+            branch_remote_and_distance(cwd, branch, remotes).await
+        else {
+            continue;
+        };
+        let Some(remote_sha) = maybe_remote_sha else {
+            // Preserve existing behavior: skip branches that are not present on a remote.
+            continue;
+        };
+        match &closest_sha {
+            None => closest_sha = Some((remote_sha, distance)),
+            Some((_, best_distance)) if distance < *best_distance => {
+                closest_sha = Some((remote_sha, distance));
+            }
+            _ => {}
+        }
+    }
+    closest_sha.map(|(sha, _)| sha)
+}
+
+async fn diff_against_sha(cwd: &Path, sha: &GitSha) -> Option<String> {
+    let output = run_git_command_with_timeout(&["diff", &sha.0], cwd).await?;
+    // 0 is success and no diff.
+    // 1 is success but there is a diff.
+    let exit_ok = output.status.code().is_some_and(|c| c == 0 || c == 1);
+    if !exit_ok {
+        return None;
+    }
+    let mut diff = String::from_utf8(output.stdout).ok()?;
+
+    if let Some(untracked_output) =
+        run_git_command_with_timeout(&["ls-files", "--others", "--exclude-standard"], cwd).await
+        && untracked_output.status.success()
+    {
+        let untracked: Vec<String> = String::from_utf8(untracked_output.stdout)
+            .ok()?
+            .lines()
+            .map(|s| s.to_string())
+            .filter(|s| !s.is_empty())
+            .collect();
+
+        if !untracked.is_empty() {
+            let futures_iter = untracked.into_iter().map(|file| async move {
+                let file_owned = file;
+                let args_vec: Vec<&str> =
+                    vec!["diff", "--binary", "--no-index", "/dev/null", &file_owned];
+                run_git_command_with_timeout(&args_vec, cwd).await
+            });
+            let results = join_all(futures_iter).await;
+            for extra in results.into_iter().flatten() {
+                if extra.status.code().is_some_and(|c| c == 0 || c == 1)
+                    && let Ok(s) = String::from_utf8(extra.stdout)
+                {
+                    diff.push_str(&s);
+                }
+            }
+        }
+    }
+
+    Some(diff)
+}
+
+/// Resolve the path that should be used for trust checks. Similar to
+/// `[utils::is_inside_git_repo]`, but resolves to the root of the main
+/// repository. Handles worktrees.
+pub fn resolve_root_git_project_for_trust(cwd: &Path) -> Option<PathBuf> {
+    let base = if cwd.is_dir() { cwd } else { cwd.parent()? };
+
+    // TODO: we should make this async, but it's primarily used deep in
+    // callstacks of sync code, and should almost always be fast
+    let git_dir_out = std::process::Command::new("git")
+        .args(["rev-parse", "--git-common-dir"])
+        .current_dir(base)
+        .output()
+        .ok()?;
+    if !git_dir_out.status.success() {
+        return None;
+    }
+    let git_dir_s = String::from_utf8(git_dir_out.stdout)
+        .ok()?
+        .trim()
+        .to_string();
+
+    let git_dir_path_raw = if Path::new(&git_dir_s).is_absolute() {
+        PathBuf::from(&git_dir_s)
+    } else {
+        base.join(&git_dir_s)
+    };
+
+    // Normalize to handle macOS /var vs /private/var and resolve ".." segments.
+    let git_dir_path = std::fs::canonicalize(&git_dir_path_raw).unwrap_or(git_dir_path_raw);
+    git_dir_path.parent().map(Path::to_path_buf)
+}
+
 #[cfg(test)]
 mod tests {
     use super::*;
@@ -107,7 +468,8 @@ mod tests {
 
     // Helper function to create a test git repository
     async fn create_test_git_repo(temp_dir: &TempDir) -> PathBuf {
-        let repo_path = temp_dir.path().to_path_buf();
+        let repo_path = temp_dir.path().join("repo");
+        fs::create_dir(&repo_path).expect("Failed to create repo dir");
         let envs = vec![
             ("GIT_CONFIG_GLOBAL", "/dev/null"),
             ("GIT_CONFIG_NOSYSTEM", "1"),
@@ -162,6 +524,41 @@ mod tests {
         repo_path
     }
 
+    async fn create_test_git_repo_with_remote(temp_dir: &TempDir) -> (PathBuf, String) {
+        let repo_path = create_test_git_repo(temp_dir).await;
+        let remote_path = temp_dir.path().join("remote.git");
+
+        Command::new("git")
+            .args(["init", "--bare", remote_path.to_str().unwrap()])
+            .output()
+            .await
+            .expect("Failed to init bare remote");
+
+        Command::new("git")
+            .args(["remote", "add", "origin", remote_path.to_str().unwrap()])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to add remote");
+
+        let output = Command::new("git")
+            .args(["rev-parse", "--abbrev-ref", "HEAD"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to get branch");
+        let branch = String::from_utf8(output.stdout).unwrap().trim().to_string();
+
+        Command::new("git")
+            .args(["push", "-u", "origin", &branch])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to push initial commit");
+
+        (repo_path, branch)
+    }
+
     #[tokio::test]
     async fn test_collect_git_info_non_git_directory() {
         let temp_dir = TempDir::new().expect("Failed to create temp dir");
@@ -275,6 +672,210 @@ mod tests {
         assert_eq!(git_info.branch, Some("feature-branch".to_string()));
     }
 
+    #[tokio::test]
+    async fn test_get_git_working_tree_state_clean_repo() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let (repo_path, branch) = create_test_git_repo_with_remote(&temp_dir).await;
+
+        let remote_sha = Command::new("git")
+            .args(["rev-parse", &format!("origin/{branch}")])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to rev-parse remote");
+        let remote_sha = String::from_utf8(remote_sha.stdout)
+            .unwrap()
+            .trim()
+            .to_string();
+
+        let state = git_diff_to_remote(&repo_path)
+            .await
+            .expect("Should collect working tree state");
+        assert_eq!(state.sha, GitSha::new(&remote_sha));
+        assert!(state.diff.is_empty());
+    }
+
+    #[tokio::test]
+    async fn test_get_git_working_tree_state_with_changes() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let (repo_path, branch) = create_test_git_repo_with_remote(&temp_dir).await;
+
+        let tracked = repo_path.join("test.txt");
+        fs::write(&tracked, "modified").unwrap();
+        fs::write(repo_path.join("untracked.txt"), "new").unwrap();
+
+        let remote_sha = Command::new("git")
+            .args(["rev-parse", &format!("origin/{branch}")])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to rev-parse remote");
+        let remote_sha = String::from_utf8(remote_sha.stdout)
+            .unwrap()
+            .trim()
+            .to_string();
+
+        let state = git_diff_to_remote(&repo_path)
+            .await
+            .expect("Should collect working tree state");
+        assert_eq!(state.sha, GitSha::new(&remote_sha));
+        assert!(state.diff.contains("test.txt"));
+        assert!(state.diff.contains("untracked.txt"));
+    }
+
+    #[tokio::test]
+    async fn test_get_git_working_tree_state_branch_fallback() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let (repo_path, _branch) = create_test_git_repo_with_remote(&temp_dir).await;
+
+        Command::new("git")
+            .args(["checkout", "-b", "feature"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to create feature branch");
+        Command::new("git")
+            .args(["push", "-u", "origin", "feature"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to push feature branch");
+
+        Command::new("git")
+            .args(["checkout", "-b", "local-branch"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to create local branch");
+
+        let remote_sha = Command::new("git")
+            .args(["rev-parse", "origin/feature"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to rev-parse remote");
+        let remote_sha = String::from_utf8(remote_sha.stdout)
+            .unwrap()
+            .trim()
+            .to_string();
+
+        let state = git_diff_to_remote(&repo_path)
+            .await
+            .expect("Should collect working tree state");
+        assert_eq!(state.sha, GitSha::new(&remote_sha));
+    }
+
+    #[test]
+    fn resolve_root_git_project_for_trust_returns_none_outside_repo() {
+        let tmp = TempDir::new().expect("tempdir");
+        assert!(resolve_root_git_project_for_trust(tmp.path()).is_none());
+    }
+
+    #[tokio::test]
+    async fn resolve_root_git_project_for_trust_regular_repo_returns_repo_root() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let repo_path = create_test_git_repo(&temp_dir).await;
+        let expected = std::fs::canonicalize(&repo_path).unwrap().to_path_buf();
+
+        assert_eq!(
+            resolve_root_git_project_for_trust(&repo_path),
+            Some(expected.clone())
+        );
+        let nested = repo_path.join("sub/dir");
+        std::fs::create_dir_all(&nested).unwrap();
+        assert_eq!(
+            resolve_root_git_project_for_trust(&nested),
+            Some(expected.clone())
+        );
+    }
+
+    #[tokio::test]
+    async fn resolve_root_git_project_for_trust_detects_worktree_and_returns_main_root() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let repo_path = create_test_git_repo(&temp_dir).await;
+
+        // Create a linked worktree
+        let wt_root = temp_dir.path().join("wt");
+        let _ = std::process::Command::new("git")
+            .args([
+                "worktree",
+                "add",
+                wt_root.to_str().unwrap(),
+                "-b",
+                "feature/x",
+            ])
+            .current_dir(&repo_path)
+            .output()
+            .expect("git worktree add");
+
+        let expected = std::fs::canonicalize(&repo_path).ok();
+        let got = resolve_root_git_project_for_trust(&wt_root)
+            .and_then(|p| std::fs::canonicalize(p).ok());
+        assert_eq!(got, expected);
+        let nested = wt_root.join("nested/sub");
+        std::fs::create_dir_all(&nested).unwrap();
+        let got_nested =
+            resolve_root_git_project_for_trust(&nested).and_then(|p| std::fs::canonicalize(p).ok());
+        assert_eq!(got_nested, expected);
+    }
+
+    #[test]
+    fn resolve_root_git_project_for_trust_non_worktrees_gitdir_returns_none() {
+        let tmp = TempDir::new().expect("tempdir");
+        let proj = tmp.path().join("proj");
+        std::fs::create_dir_all(proj.join("nested")).unwrap();
+
+        // `.git` is a file but does not point to a worktrees path
+        std::fs::write(
+            proj.join(".git"),
+            format!(
+                "gitdir: {}\n",
+                tmp.path().join("some/other/location").display()
+            ),
+        )
+        .unwrap();
+
+        assert!(resolve_root_git_project_for_trust(&proj).is_none());
+        assert!(resolve_root_git_project_for_trust(&proj.join("nested")).is_none());
+    }
+
+    #[tokio::test]
+    async fn test_get_git_working_tree_state_unpushed_commit() {
+        let temp_dir = TempDir::new().expect("Failed to create temp dir");
+        let (repo_path, branch) = create_test_git_repo_with_remote(&temp_dir).await;
+
+        let remote_sha = Command::new("git")
+            .args(["rev-parse", &format!("origin/{branch}")])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to rev-parse remote");
+        let remote_sha = String::from_utf8(remote_sha.stdout)
+            .unwrap()
+            .trim()
+            .to_string();
+
+        fs::write(repo_path.join("test.txt"), "updated").unwrap();
+        Command::new("git")
+            .args(["add", "test.txt"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to add file");
+        Command::new("git")
+            .args(["commit", "-m", "local change"])
+            .current_dir(&repo_path)
+            .output()
+            .await
+            .expect("Failed to commit");
+
+        let state = git_diff_to_remote(&repo_path)
+            .await
+            .expect("Should collect working tree state");
+        assert_eq!(state.sha, GitSha::new(&remote_sha));
+        assert!(state.diff.contains("updated"));
+    }
+
     #[test]
     fn test_git_info_serialization() {
         let git_info = GitInfo {

codex-rs/core/src/is_safe_command.rs

@@ -12,20 +12,17 @@ pub fn is_known_safe_command(command: &[String]) -> bool {
     // introduce side effects ( "&&", "||", ";", and "|" ). If every
     // individual command in the script is itself a known‑safe command, then
     // the composite expression is considered safe.
-    if let [bash, flag, script] = command {
-        if bash == "bash" && flag == "-lc" {
-            if let Some(tree) = try_parse_bash(script) {
-                if let Some(all_commands) = try_parse_word_only_commands_sequence(&tree, script) {
-                    if !all_commands.is_empty()
-                        && all_commands
-                            .iter()
-                            .all(|cmd| is_safe_to_call_with_exec(cmd))
-                    {
-                        return true;
-                    }
-                }
-            }
-        }
+    if let [bash, flag, script] = command
+        && bash == "bash"
+        && flag == "-lc"
+        && let Some(tree) = try_parse_bash(script)
+        && let Some(all_commands) = try_parse_word_only_commands_sequence(&tree, script)
+        && !all_commands.is_empty()
+        && all_commands
+            .iter()
+            .all(|cmd| is_safe_to_call_with_exec(cmd))
+    {
+        return true;
     }
 
     false

codex-rs/core/src/lib.rs

@@ -20,6 +20,7 @@ mod conversation_history;
 mod environment_context;
 pub mod error;
 pub mod exec;
+mod exec_command;
 pub mod exec_env;
 mod flags;
 pub mod git_info;
@@ -39,20 +40,26 @@ mod conversation_manager;
 pub use conversation_manager::ConversationManager;
 pub use conversation_manager::NewConversation;
 pub mod model_family;
-mod models;
 mod openai_model_info;
 mod openai_tools;
 pub mod plan_tool;
-mod project_doc;
-pub mod protocol;
+pub mod project_doc;
 mod rollout;
 pub(crate) mod safety;
 pub mod seatbelt;
 pub mod shell;
 pub mod spawn;
+pub mod terminal;
+mod tool_apply_patch;
 pub mod turn_diff_tracker;
 pub mod user_agent;
 mod user_notification;
 pub mod util;
 pub use apply_patch::CODEX_APPLY_PATCH_ARG1;
 pub use safety::get_platform_sandbox;
+// Re-export the protocol types from the standalone `codex-protocol` crate so existing
+// `codex_core::protocol::...` references continue to work across the workspace.
+pub use codex_protocol::protocol;
+// Re-export protocol config enums to ensure call sites can use the same types
+// as those in the protocol crate when constructing protocol messages.
+pub use codex_protocol::config_types as protocol_config_types;

codex-rs/core/src/mcp_tool_call.rs

@@ -4,13 +4,13 @@ use std::time::Instant;
 use tracing::error;
 
 use crate::codex::Session;
-use crate::models::FunctionCallOutputPayload;
-use crate::models::ResponseInputItem;
 use crate::protocol::Event;
 use crate::protocol::EventMsg;
 use crate::protocol::McpInvocation;
 use crate::protocol::McpToolCallBeginEvent;
 use crate::protocol::McpToolCallEndEvent;
+use codex_protocol::models::FunctionCallOutputPayload;
+use codex_protocol::models::ResponseInputItem;
 
 /// Handles the specified tool call dispatches the appropriate
 /// `McpToolCallBegin` and `McpToolCallEnd` events to the `Session`.

codex-rs/core/src/message_history.rs

@@ -125,16 +125,18 @@ pub(crate) async fn append_entry(text: &str, session_id: &Uuid, config: &Config)
 /// times if the lock is currently held by another process. This prevents a
 /// potential indefinite wait while still giving other writers some time to
 /// finish their operation.
-async fn acquire_exclusive_lock_with_retry(file: &std::fs::File) -> Result<()> {
+async fn acquire_exclusive_lock_with_retry(file: &File) -> Result<()> {
     use tokio::time::sleep;
 
     for _ in 0..MAX_RETRIES {
-        match fs2::FileExt::try_lock_exclusive(file) {
+        match file.try_lock() {
             Ok(()) => return Ok(()),
-            Err(e) if e.kind() == std::io::ErrorKind::WouldBlock => {
-                sleep(RETRY_SLEEP).await;
-            }
-            Err(e) => return Err(e),
+            Err(e) => match e {
+                std::fs::TryLockError::WouldBlock => {
+                    sleep(RETRY_SLEEP).await;
+                }
+                other => return Err(other.into()),
+            },
         }
     }
 
@@ -259,12 +261,14 @@ pub(crate) fn lookup(log_id: u64, offset: usize, config: &Config) -> Option<Hist
 #[cfg(unix)]
 fn acquire_shared_lock_with_retry(file: &File) -> Result<()> {
     for _ in 0..MAX_RETRIES {
-        match fs2::FileExt::try_lock_shared(file) {
+        match file.try_lock_shared() {
             Ok(()) => return Ok(()),
-            Err(e) if e.kind() == std::io::ErrorKind::WouldBlock => {
-                std::thread::sleep(RETRY_SLEEP);
-            }
-            Err(e) => return Err(e),
+            Err(e) => match e {
+                std::fs::TryLockError::WouldBlock => {
+                    std::thread::sleep(RETRY_SLEEP);
+                }
+                other => return Err(other.into()),
+            },
         }
     }
 

codex-rs/core/src/model_family.rs

@@ -1,3 +1,5 @@
+use crate::tool_apply_patch::ApplyPatchToolType;
+
 /// A model family is a group of models that share certain characteristics.
 #[derive(Debug, Clone, PartialEq, Eq, Hash)]
 pub struct ModelFamily {
@@ -23,6 +25,10 @@ pub struct ModelFamily {
     // the model such that its description can be omitted.
     // See https://platform.openai.com/docs/guides/tools-local-shell
     pub uses_local_shell_tool: bool,
+
+    /// Present if the model performs better when `apply_patch` is provided as
+    /// a tool call instead of just a bash command
+    pub apply_patch_tool_type: Option<ApplyPatchToolType>,
 }
 
 macro_rules! model_family {
@@ -36,6 +42,7 @@ macro_rules! model_family {
             needs_special_apply_patch_instructions: false,
             supports_reasoning_summaries: false,
             uses_local_shell_tool: false,
+            apply_patch_tool_type: None,
         };
         // apply overrides
         $(
@@ -55,6 +62,7 @@ macro_rules! simple_model_family {
             needs_special_apply_patch_instructions: false,
             supports_reasoning_summaries: false,
             uses_local_shell_tool: false,
+            apply_patch_tool_type: None,
         })
     }};
 }
@@ -82,22 +90,24 @@ pub fn find_family_for_model(slug: &str) -> Option<ModelFamily> {
         model_family!(
             slug, slug,
             supports_reasoning_summaries: true,
+            apply_patch_tool_type: Some(ApplyPatchToolType::Freeform),
         )
     } else if slug.starts_with("gpt-4.1") {
         model_family!(
             slug, "gpt-4.1",
             needs_special_apply_patch_instructions: true,
         )
+    } else if slug.starts_with("gpt-oss") {
+        model_family!(slug, "gpt-oss", apply_patch_tool_type: Some(ApplyPatchToolType::Function))
     } else if slug.starts_with("gpt-4o") {
         simple_model_family!(slug, "gpt-4o")
-    } else if slug.starts_with("gpt-oss") {
-        simple_model_family!(slug, "gpt-oss")
     } else if slug.starts_with("gpt-3.5") {
         simple_model_family!(slug, "gpt-3.5")
     } else if slug.starts_with("gpt-5") {
         model_family!(
             slug, "gpt-5",
             supports_reasoning_summaries: true,
+            apply_patch_tool_type: Some(ApplyPatchToolType::Freeform),
         )
     } else {
         None

codex-rs/core/src/model_provider_info.rs

@@ -167,10 +167,10 @@ impl ModelProviderInfo {
 
         if let Some(env_headers) = &self.env_http_headers {
             for (header, env_var) in env_headers {
-                if let Ok(val) = std::env::var(env_var) {
-                    if !val.trim().is_empty() {
-                        builder = builder.header(header, val);
-                    }
+                if let Ok(val) = std::env::var(env_var)
+                    && !val.trim().is_empty()
+                {
+                    builder = builder.header(header, val);
                 }
             }
         }

codex-rs/core/src/openai_tools.rs

@@ -9,6 +9,9 @@ use crate::model_family::ModelFamily;
 use crate::plan_tool::PLAN_TOOL;
 use crate::protocol::AskForApproval;
 use crate::protocol::SandboxPolicy;
+use crate::tool_apply_patch::ApplyPatchToolType;
+use crate::tool_apply_patch::create_apply_patch_freeform_tool;
+use crate::tool_apply_patch::create_apply_patch_json_tool;
 
 #[derive(Debug, Clone, Serialize, PartialEq)]
 pub struct ResponsesApiTool {
@@ -21,6 +24,20 @@ pub struct ResponsesApiTool {
     pub(crate) parameters: JsonSchema,
 }
 
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
+pub struct FreeformTool {
+    pub(crate) name: String,
+    pub(crate) description: String,
+    pub(crate) format: FreeformToolFormat,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq)]
+pub struct FreeformToolFormat {
+    pub(crate) r#type: String,
+    pub(crate) syntax: String,
+    pub(crate) definition: String,
+}
+
 /// When serialized as JSON, this produces a valid "Tool" in the OpenAI
 /// Responses API.
 #[derive(Debug, Clone, Serialize, PartialEq)]
@@ -30,6 +47,8 @@ pub(crate) enum OpenAiTool {
     Function(ResponsesApiTool),
     #[serde(rename = "local_shell")]
     LocalShell {},
+    #[serde(rename = "custom")]
+    Freeform(FreeformTool),
 }
 
 #[derive(Debug, Clone)]
@@ -37,12 +56,14 @@ pub enum ConfigShellToolType {
     DefaultShell,
     ShellWithRequest { sandbox_policy: SandboxPolicy },
     LocalShell,
+    StreamableShell,
 }
 
 #[derive(Debug, Clone)]
 pub struct ToolsConfig {
     pub shell_type: ConfigShellToolType,
     pub plan_tool: bool,
+    pub apply_patch_tool_type: Option<ApplyPatchToolType>,
 }
 
 impl ToolsConfig {
@@ -51,21 +72,38 @@ impl ToolsConfig {
         approval_policy: AskForApproval,
         sandbox_policy: SandboxPolicy,
         include_plan_tool: bool,
+        include_apply_patch_tool: bool,
+        use_streamable_shell_tool: bool,
     ) -> Self {
-        let mut shell_type = if model_family.uses_local_shell_tool {
+        let mut shell_type = if use_streamable_shell_tool {
+            ConfigShellToolType::StreamableShell
+        } else if model_family.uses_local_shell_tool {
             ConfigShellToolType::LocalShell
         } else {
             ConfigShellToolType::DefaultShell
         };
-        if matches!(approval_policy, AskForApproval::OnRequest) {
+        if matches!(approval_policy, AskForApproval::OnRequest) && !use_streamable_shell_tool {
             shell_type = ConfigShellToolType::ShellWithRequest {
                 sandbox_policy: sandbox_policy.clone(),
             }
         }
 
+        let apply_patch_tool_type = match model_family.apply_patch_tool_type {
+            Some(ApplyPatchToolType::Freeform) => Some(ApplyPatchToolType::Freeform),
+            Some(ApplyPatchToolType::Function) => Some(ApplyPatchToolType::Function),
+            None => {
+                if include_apply_patch_tool {
+                    Some(ApplyPatchToolType::Freeform)
+                } else {
+                    None
+                }
+            }
+        };
+
         Self {
             shell_type,
             plan_tool: include_plan_tool,
+            apply_patch_tool_type,
         }
     }
 }
@@ -112,16 +150,20 @@ fn create_shell_tool() -> OpenAiTool {
         "command".to_string(),
         JsonSchema::Array {
             items: Box::new(JsonSchema::String { description: None }),
-            description: None,
+            description: Some("The command to execute".to_string()),
         },
     );
     properties.insert(
         "workdir".to_string(),
-        JsonSchema::String { description: None },
+        JsonSchema::String {
+            description: Some("The working directory to execute the command in".to_string()),
+        },
     );
     properties.insert(
-        "timeout".to_string(),
-        JsonSchema::Number { description: None },
+        "timeout_ms".to_string(),
+        JsonSchema::Number {
+            description: Some("The timeout for the command in milliseconds".to_string()),
+        },
     );
 
     OpenAiTool::Function(ResponsesApiTool {
@@ -152,7 +194,7 @@ fn create_shell_tool_for_sandbox(sandbox_policy: &SandboxPolicy) -> OpenAiTool {
         },
     );
     properties.insert(
-        "timeout".to_string(),
+        "timeout_ms".to_string(),
         JsonSchema::Number {
             description: Some("The timeout for the command in milliseconds".to_string()),
         },
@@ -168,7 +210,7 @@ fn create_shell_tool_for_sandbox(sandbox_policy: &SandboxPolicy) -> OpenAiTool {
         properties.insert(
         "justification".to_string(),
         JsonSchema::String {
-            description: Some("Only set if ask_for_escalated_permissions is true. 1-sentence explanation of why we want to run this command.".to_string()),
+            description: Some("Only set if with_escalated_permissions is true. 1-sentence explanation of why we want to run this command.".to_string()),
         },
     );
     }
@@ -234,11 +276,16 @@ The shell tool is used to execute shell commands.
         },
     })
 }
+/// TODO(dylan): deprecate once we get rid of json tool
+#[derive(Serialize, Deserialize)]
+pub(crate) struct ApplyPatchToolArgs {
+    pub(crate) input: String,
+}
 
 /// Returns JSON values that are compatible with Function Calling in the
 /// Responses API:
 /// https://platform.openai.com/docs/guides/function-calling?api-mode=responses
-pub(crate) fn create_tools_json_for_responses_api(
+pub fn create_tools_json_for_responses_api(
     tools: &Vec<OpenAiTool>,
 ) -> crate::error::Result<Vec<serde_json::Value>> {
     let mut tools_json = Vec::new();
@@ -336,11 +383,11 @@ fn sanitize_json_schema(value: &mut JsonValue) {
         }
         JsonValue::Object(map) => {
             // First, recursively sanitize known nested schema holders
-            if let Some(props) = map.get_mut("properties") {
-                if let Some(props_map) = props.as_object_mut() {
-                    for (_k, v) in props_map.iter_mut() {
-                        sanitize_json_schema(v);
-                    }
+            if let Some(props) = map.get_mut("properties")
+                && let Some(props_map) = props.as_object_mut()
+            {
+                for (_k, v) in props_map.iter_mut() {
+                    sanitize_json_schema(v);
                 }
             }
             if let Some(items) = map.get_mut("items") {
@@ -360,18 +407,18 @@ fn sanitize_json_schema(value: &mut JsonValue) {
                 .map(|s| s.to_string());
 
             // If type is an array (union), pick first supported; else leave to inference
-            if ty.is_none() {
-                if let Some(JsonValue::Array(types)) = map.get("type") {
-                    for t in types {
-                        if let Some(tt) = t.as_str() {
-                            if matches!(
-                                tt,
-                                "object" | "array" | "string" | "number" | "integer" | "boolean"
-                            ) {
-                                ty = Some(tt.to_string());
-                                break;
-                            }
-                        }
+            if ty.is_none()
+                && let Some(JsonValue::Array(types)) = map.get("type")
+            {
+                for t in types {
+                    if let Some(tt) = t.as_str()
+                        && matches!(
+                            tt,
+                            "object" | "array" | "string" | "number" | "integer" | "boolean"
+                        )
+                    {
+                        ty = Some(tt.to_string());
+                        break;
                     }
                 }
             }
@@ -449,12 +496,31 @@ pub(crate) fn get_openai_tools(
         ConfigShellToolType::LocalShell => {
             tools.push(OpenAiTool::LocalShell {});
         }
+        ConfigShellToolType::StreamableShell => {
+            tools.push(OpenAiTool::Function(
+                crate::exec_command::create_exec_command_tool_for_responses_api(),
+            ));
+            tools.push(OpenAiTool::Function(
+                crate::exec_command::create_write_stdin_tool_for_responses_api(),
+            ));
+        }
     }
 
     if config.plan_tool {
         tools.push(PLAN_TOOL.clone());
     }
 
+    if let Some(apply_patch_tool_type) = &config.apply_patch_tool_type {
+        match apply_patch_tool_type {
+            ApplyPatchToolType::Freeform => {
+                tools.push(create_apply_patch_freeform_tool());
+            }
+            ApplyPatchToolType::Function => {
+                tools.push(create_apply_patch_json_tool());
+            }
+        }
+    }
+
     if let Some(mcp_tools) = mcp_tools {
         for (name, tool) in mcp_tools {
             match mcp_tool_to_openai_tool(name.clone(), tool.clone()) {
@@ -483,6 +549,7 @@ mod tests {
             .map(|tool| match tool {
                 OpenAiTool::Function(ResponsesApiTool { name, .. }) => name,
                 OpenAiTool::LocalShell {} => "local_shell",
+                OpenAiTool::Freeform(FreeformTool { name, .. }) => name,
             })
             .collect::<Vec<_>>();
 
@@ -508,6 +575,8 @@ mod tests {
             AskForApproval::Never,
             SandboxPolicy::ReadOnly,
             true,
+            false,
+            /*use_experimental_streamable_shell_tool*/ false,
         );
         let tools = get_openai_tools(&config, Some(HashMap::new()));
 
@@ -522,6 +591,8 @@ mod tests {
             AskForApproval::Never,
             SandboxPolicy::ReadOnly,
             true,
+            false,
+            /*use_experimental_streamable_shell_tool*/ false,
         );
         let tools = get_openai_tools(&config, Some(HashMap::new()));
 
@@ -536,6 +607,8 @@ mod tests {
             AskForApproval::Never,
             SandboxPolicy::ReadOnly,
             false,
+            false,
+            /*use_experimental_streamable_shell_tool*/ false,
         );
         let tools = get_openai_tools(
             &config,
@@ -629,6 +702,8 @@ mod tests {
             AskForApproval::Never,
             SandboxPolicy::ReadOnly,
             false,
+            false,
+            /*use_experimental_streamable_shell_tool*/ false,
         );
 
         let tools = get_openai_tools(
@@ -684,6 +759,8 @@ mod tests {
             AskForApproval::Never,
             SandboxPolicy::ReadOnly,
             false,
+            false,
+            /*use_experimental_streamable_shell_tool*/ false,
         );
 
         let tools = get_openai_tools(
@@ -734,6 +811,8 @@ mod tests {
             AskForApproval::Never,
             SandboxPolicy::ReadOnly,
             false,
+            false,
+            /*use_experimental_streamable_shell_tool*/ false,
         );
 
         let tools = get_openai_tools(
@@ -787,6 +866,8 @@ mod tests {
             AskForApproval::Never,
             SandboxPolicy::ReadOnly,
             false,
+            false,
+            /*use_experimental_streamable_shell_tool*/ false,
         );
 
         let tools = get_openai_tools(

codex-rs/core/src/parse_command.rs

@@ -41,6 +41,24 @@ pub enum ParsedCommand {
     },
 }
 
+// Convert core's parsed command enum into the protocol's simplified type so
+// events can carry the canonical representation across process boundaries.
+impl From<ParsedCommand> for codex_protocol::parse_command::ParsedCommand {
+    fn from(v: ParsedCommand) -> Self {
+        use codex_protocol::parse_command::ParsedCommand as P;
+        match v {
+            ParsedCommand::Read { cmd, name } => P::Read { cmd, name },
+            ParsedCommand::ListFiles { cmd, path } => P::ListFiles { cmd, path },
+            ParsedCommand::Search { cmd, query, path } => P::Search { cmd, query, path },
+            ParsedCommand::Format { cmd, tool, targets } => P::Format { cmd, tool, targets },
+            ParsedCommand::Test { cmd } => P::Test { cmd },
+            ParsedCommand::Lint { cmd, tool, targets } => P::Lint { cmd, tool, targets },
+            ParsedCommand::Noop { cmd } => P::Noop { cmd },
+            ParsedCommand::Unknown { cmd } => P::Unknown { cmd },
+        }
+    }
+}
+
 fn shlex_join(tokens: &[String]) -> String {
     shlex_try_join(tokens.iter().map(|s| s.as_str()))
         .unwrap_or_else(|_| "<command included NUL byte>".to_string())
@@ -1178,10 +1196,10 @@ fn simplify_once(commands: &[ParsedCommand]) -> Option<Vec<ParsedCommand>> {
     }
 
     // echo ... && ...rest => ...rest
-    if let ParsedCommand::Unknown { cmd } = &commands[0] {
-        if shlex_split(cmd).is_some_and(|t| t.first().map(|s| s.as_str()) == Some("echo")) {
-            return Some(commands[1..].to_vec());
-        }
+    if let ParsedCommand::Unknown { cmd } = &commands[0]
+        && shlex_split(cmd).is_some_and(|t| t.first().map(|s| s.as_str()) == Some("echo"))
+    {
+        return Some(commands[1..].to_vec());
     }
 
     // cd foo && [any Test command] => [any Test command]
@@ -1190,17 +1208,15 @@ fn simplify_once(commands: &[ParsedCommand]) -> Option<Vec<ParsedCommand>> {
             shlex_split(cmd).is_some_and(|t| t.first().map(|s| s.as_str()) == Some("cd"))
         }
         _ => false,
-    }) {
-        if commands
-            .iter()
-            .skip(idx + 1)
-            .any(|pc| matches!(pc, ParsedCommand::Test { .. }))
-        {
-            let mut out = Vec::with_capacity(commands.len() - 1);
-            out.extend_from_slice(&commands[..idx]);
-            out.extend_from_slice(&commands[idx + 1..]);
-            return Some(out);
-        }
+    }) && commands
+        .iter()
+        .skip(idx + 1)
+        .any(|pc| matches!(pc, ParsedCommand::Test { .. }))
+    {
+        let mut out = Vec::with_capacity(commands.len() - 1);
+        out.extend_from_slice(&commands[..idx]);
+        out.extend_from_slice(&commands[idx + 1..]);
+        return Some(out);
     }
 
     // cmd || true => cmd
@@ -1546,127 +1562,124 @@ fn parse_bash_lc_commands(original: &[String]) -> Option<Vec<ParsedCommand>> {
     if bash != "bash" || flag != "-lc" {
         return None;
     }
-    if let Some(tree) = try_parse_bash(script) {
-        if let Some(all_commands) = try_parse_word_only_commands_sequence(&tree, script) {
-            if !all_commands.is_empty() {
-                let script_tokens = shlex_split(script)
-                    .unwrap_or_else(|| vec!["bash".to_string(), flag.clone(), script.clone()]);
-                // Strip small formatting helpers (e.g., head/tail/awk/wc/etc) so we
-                // bias toward the primary command when pipelines are present.
-                // First, drop obvious small formatting helpers (e.g., wc/awk/etc).
-                let had_multiple_commands = all_commands.len() > 1;
-                // The bash AST walker yields commands in right-to-left order for
-                // connector/pipeline sequences. Reverse to reflect actual execution order.
-                let mut filtered_commands = drop_small_formatting_commands(all_commands);
-                filtered_commands.reverse();
-                if filtered_commands.is_empty() {
-                    return Some(vec![ParsedCommand::Unknown {
-                        cmd: script.clone(),
-                    }]);
-                }
-                let mut commands: Vec<ParsedCommand> = filtered_commands
-                    .into_iter()
-                    .map(|tokens| summarize_main_tokens(&tokens))
-                    .collect();
-                if commands.len() > 1 {
-                    commands.retain(|pc| !matches!(pc, ParsedCommand::Noop { .. }));
-                }
-                if commands.len() == 1 {
-                    // If we reduced to a single command, attribute the full original script
-                    // for clearer UX in file-reading and listing scenarios, or when there were
-                    // no connectors in the original script. For search commands that came from
-                    // a pipeline (e.g. `rg --files | sed -n`), keep only the primary command.
-                    let had_connectors = had_multiple_commands
-                        || script_tokens
-                            .iter()
-                            .any(|t| t == "|" || t == "&&" || t == "||" || t == ";");
-                    commands = commands
-                        .into_iter()
-                        .map(|pc| match pc {
-                            ParsedCommand::Read { name, cmd, .. } => {
-                                if had_connectors {
-                                    let has_pipe = script_tokens.iter().any(|t| t == "|");
-                                    let has_sed_n = script_tokens.windows(2).any(|w| {
-                                        w.first().map(|s| s.as_str()) == Some("sed")
-                                            && w.get(1).map(|s| s.as_str()) == Some("-n")
-                                    });
-                                    if has_pipe && has_sed_n {
-                                        ParsedCommand::Read {
-                                            cmd: script.clone(),
-                                            name,
-                                        }
-                                    } else {
-                                        ParsedCommand::Read {
-                                            cmd: cmd.clone(),
-                                            name,
-                                        }
-                                    }
-                                } else {
-                                    ParsedCommand::Read {
-                                        cmd: shlex_join(&script_tokens),
-                                        name,
-                                    }
-                                }
-                            }
-                            ParsedCommand::ListFiles { path, cmd, .. } => {
-                                if had_connectors {
-                                    ParsedCommand::ListFiles {
-                                        cmd: cmd.clone(),
-                                        path,
-                                    }
-                                } else {
-                                    ParsedCommand::ListFiles {
-                                        cmd: shlex_join(&script_tokens),
-                                        path,
-                                    }
-                                }
-                            }
-                            ParsedCommand::Search {
-                                query, path, cmd, ..
-                            } => {
-                                if had_connectors {
-                                    ParsedCommand::Search {
-                                        cmd: cmd.clone(),
-                                        query,
-                                        path,
-                                    }
-                                } else {
-                                    ParsedCommand::Search {
-                                        cmd: shlex_join(&script_tokens),
-                                        query,
-                                        path,
-                                    }
-                                }
-                            }
-                            ParsedCommand::Format {
-                                tool, targets, cmd, ..
-                            } => ParsedCommand::Format {
-                                cmd: cmd.clone(),
-                                tool,
-                                targets,
-                            },
-                            ParsedCommand::Test { cmd, .. } => {
-                                ParsedCommand::Test { cmd: cmd.clone() }
-                            }
-                            ParsedCommand::Lint {
-                                tool, targets, cmd, ..
-                            } => ParsedCommand::Lint {
-                                cmd: cmd.clone(),
-                                tool,
-                                targets,
-                            },
-                            ParsedCommand::Unknown { .. } => ParsedCommand::Unknown {
-                                cmd: script.clone(),
-                            },
-                            ParsedCommand::Noop { .. } => ParsedCommand::Noop {
-                                cmd: script.clone(),
-                            },
-                        })
-                        .collect();
-                }
-                return Some(commands);
-            }
+    if let Some(tree) = try_parse_bash(script)
+        && let Some(all_commands) = try_parse_word_only_commands_sequence(&tree, script)
+        && !all_commands.is_empty()
+    {
+        let script_tokens = shlex_split(script)
+            .unwrap_or_else(|| vec!["bash".to_string(), flag.clone(), script.clone()]);
+        // Strip small formatting helpers (e.g., head/tail/awk/wc/etc) so we
+        // bias toward the primary command when pipelines are present.
+        // First, drop obvious small formatting helpers (e.g., wc/awk/etc).
+        let had_multiple_commands = all_commands.len() > 1;
+        // The bash AST walker yields commands in right-to-left order for
+        // connector/pipeline sequences. Reverse to reflect actual execution order.
+        let mut filtered_commands = drop_small_formatting_commands(all_commands);
+        filtered_commands.reverse();
+        if filtered_commands.is_empty() {
+            return Some(vec![ParsedCommand::Unknown {
+                cmd: script.clone(),
+            }]);
         }
+        let mut commands: Vec<ParsedCommand> = filtered_commands
+            .into_iter()
+            .map(|tokens| summarize_main_tokens(&tokens))
+            .collect();
+        if commands.len() > 1 {
+            commands.retain(|pc| !matches!(pc, ParsedCommand::Noop { .. }));
+        }
+        if commands.len() == 1 {
+            // If we reduced to a single command, attribute the full original script
+            // for clearer UX in file-reading and listing scenarios, or when there were
+            // no connectors in the original script. For search commands that came from
+            // a pipeline (e.g. `rg --files | sed -n`), keep only the primary command.
+            let had_connectors = had_multiple_commands
+                || script_tokens
+                    .iter()
+                    .any(|t| t == "|" || t == "&&" || t == "||" || t == ";");
+            commands = commands
+                .into_iter()
+                .map(|pc| match pc {
+                    ParsedCommand::Read { name, cmd, .. } => {
+                        if had_connectors {
+                            let has_pipe = script_tokens.iter().any(|t| t == "|");
+                            let has_sed_n = script_tokens.windows(2).any(|w| {
+                                w.first().map(|s| s.as_str()) == Some("sed")
+                                    && w.get(1).map(|s| s.as_str()) == Some("-n")
+                            });
+                            if has_pipe && has_sed_n {
+                                ParsedCommand::Read {
+                                    cmd: script.clone(),
+                                    name,
+                                }
+                            } else {
+                                ParsedCommand::Read {
+                                    cmd: cmd.clone(),
+                                    name,
+                                }
+                            }
+                        } else {
+                            ParsedCommand::Read {
+                                cmd: shlex_join(&script_tokens),
+                                name,
+                            }
+                        }
+                    }
+                    ParsedCommand::ListFiles { path, cmd, .. } => {
+                        if had_connectors {
+                            ParsedCommand::ListFiles {
+                                cmd: cmd.clone(),
+                                path,
+                            }
+                        } else {
+                            ParsedCommand::ListFiles {
+                                cmd: shlex_join(&script_tokens),
+                                path,
+                            }
+                        }
+                    }
+                    ParsedCommand::Search {
+                        query, path, cmd, ..
+                    } => {
+                        if had_connectors {
+                            ParsedCommand::Search {
+                                cmd: cmd.clone(),
+                                query,
+                                path,
+                            }
+                        } else {
+                            ParsedCommand::Search {
+                                cmd: shlex_join(&script_tokens),
+                                query,
+                                path,
+                            }
+                        }
+                    }
+                    ParsedCommand::Format {
+                        tool, targets, cmd, ..
+                    } => ParsedCommand::Format {
+                        cmd: cmd.clone(),
+                        tool,
+                        targets,
+                    },
+                    ParsedCommand::Test { cmd, .. } => ParsedCommand::Test { cmd: cmd.clone() },
+                    ParsedCommand::Lint {
+                        tool, targets, cmd, ..
+                    } => ParsedCommand::Lint {
+                        cmd: cmd.clone(),
+                        tool,
+                        targets,
+                    },
+                    ParsedCommand::Unknown { .. } => ParsedCommand::Unknown {
+                        cmd: script.clone(),
+                    },
+                    ParsedCommand::Noop { .. } => ParsedCommand::Noop {
+                        cmd: script.clone(),
+                    },
+                })
+                .collect();
+        }
+        return Some(commands);
     }
     Some(vec![ParsedCommand::Unknown {
         cmd: script.clone(),

codex-rs/core/src/plan_tool.rs

@@ -1,41 +1,22 @@
 use std::collections::BTreeMap;
 use std::sync::LazyLock;
 
-use serde::Deserialize;
-use serde::Serialize;
-
 use crate::codex::Session;
-use crate::models::FunctionCallOutputPayload;
-use crate::models::ResponseInputItem;
 use crate::openai_tools::JsonSchema;
 use crate::openai_tools::OpenAiTool;
 use crate::openai_tools::ResponsesApiTool;
 use crate::protocol::Event;
 use crate::protocol::EventMsg;
+use codex_protocol::models::FunctionCallOutputPayload;
+use codex_protocol::models::ResponseInputItem;
+
+// Use the canonical plan tool types from the protocol crate to ensure
+// type-identity matches events transported via `codex_protocol`.
+pub use codex_protocol::plan_tool::PlanItemArg;
+pub use codex_protocol::plan_tool::StepStatus;
+pub use codex_protocol::plan_tool::UpdatePlanArgs;
 
 // Types for the TODO tool arguments matching codex-vscode/todo-mcp/src/main.rs
-#[derive(Debug, Clone, Serialize, Deserialize)]
-#[serde(rename_all = "snake_case")]
-pub enum StepStatus {
-    Pending,
-    InProgress,
-    Completed,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-#[serde(deny_unknown_fields)]
-pub struct PlanItemArg {
-    pub step: String,
-    pub status: StepStatus,
-}
-
-#[derive(Debug, Clone, Serialize, Deserialize)]
-#[serde(deny_unknown_fields)]
-pub struct UpdatePlanArgs {
-    #[serde(default)]
-    pub explanation: Option<String>,
-    pub plan: Vec<PlanItemArg>,
-}
 
 pub(crate) static PLAN_TOOL: LazyLock<OpenAiTool> = LazyLock::new(|| {
     let mut plan_item_props = BTreeMap::new();

codex-rs/core/src/project_doc.rs

@@ -1,18 +1,19 @@
 //! Project-level documentation discovery.
 //!
-//! Project-level documentation can be stored in a file named `AGENTS.md`.
-//! Currently, we include only the contents of the first file found as follows:
+//! Project-level documentation can be stored in files named `AGENTS.md`.
+//! We include the concatenation of all files found along the path from the
+//! repository root to the current working directory as follows:
 //!
-//! 1.  Look for the doc file in the current working directory (as determined
-//!     by the `Config`).
-//! 2.  If not found, walk *upwards* until the Git repository root is reached
-//!     (detected by the presence of a `.git` directory/file), or failing that,
-//!     the filesystem root.
-//! 3.  If the Git root is encountered, look for the doc file there. If it
-//!     exists, the search stops – we do **not** walk past the Git root.
+//! 1.  Determine the Git repository root by walking upwards from the current
+//!     working directory until a `.git` directory or file is found. If no Git
+//!     root is found, only the current working directory is considered.
+//! 2.  Collect every `AGENTS.md` found from the repository root down to the
+//!     current working directory (inclusive) and concatenate their contents in
+//!     that order.
+//! 3.  We do **not** walk past the Git root.
 
 use crate::config::Config;
-use std::path::Path;
+use std::path::PathBuf;
 use tokio::io::AsyncReadExt;
 use tracing::error;
 
@@ -26,7 +27,7 @@ const PROJECT_DOC_SEPARATOR: &str = "\n\n--- project-doc ---\n\n";
 /// Combines `Config::instructions` and `AGENTS.md` (if present) into a single
 /// string of instructions.
 pub(crate) async fn get_user_instructions(config: &Config) -> Option<String> {
-    match find_project_doc(config).await {
+    match read_project_docs(config).await {
         Ok(Some(project_doc)) => match &config.user_instructions {
             Some(original_instructions) => Some(format!(
                 "{original_instructions}{PROJECT_DOC_SEPARATOR}{project_doc}"
@@ -41,95 +42,135 @@ pub(crate) async fn get_user_instructions(config: &Config) -> Option<String> {
     }
 }
 
-/// Attempt to locate and load the project documentation. Currently, the search
-/// starts from `Config::cwd`, but if we may want to consider other directories
-/// in the future, e.g., additional writable directories in the `SandboxPolicy`.
+/// Attempt to locate and load the project documentation.
 ///
-/// On success returns `Ok(Some(contents))`. If no documentation file is found
-/// the function returns `Ok(None)`. Unexpected I/O failures bubble up as
-/// `Err` so callers can decide how to handle them.
-async fn find_project_doc(config: &Config) -> std::io::Result<Option<String>> {
-    let max_bytes = config.project_doc_max_bytes;
+/// On success returns `Ok(Some(contents))` where `contents` is the
+/// concatenation of all discovered docs. If no documentation file is found the
+/// function returns `Ok(None)`. Unexpected I/O failures bubble up as `Err` so
+/// callers can decide how to handle them.
+pub async fn read_project_docs(config: &Config) -> std::io::Result<Option<String>> {
+    let max_total = config.project_doc_max_bytes;
 
-    // Attempt to load from the working directory first.
-    if let Some(doc) = load_first_candidate(&config.cwd, CANDIDATE_FILENAMES, max_bytes).await? {
-        return Ok(Some(doc));
+    if max_total == 0 {
+        return Ok(None);
     }
 
-    // Walk up towards the filesystem root, stopping once we encounter the Git
-    // repository root. The presence of **either** a `.git` *file* or
-    // *directory* counts.
-    let mut dir = config.cwd.clone();
+    let paths = discover_project_doc_paths(config)?;
+    if paths.is_empty() {
+        return Ok(None);
+    }
 
-    // Canonicalize the path so that we do not end up in an infinite loop when
-    // `cwd` contains `..` components.
+    let mut remaining: u64 = max_total as u64;
+    let mut parts: Vec<String> = Vec::new();
+
+    for p in paths {
+        if remaining == 0 {
+            break;
+        }
+
+        let file = match tokio::fs::File::open(&p).await {
+            Ok(f) => f,
+            Err(e) if e.kind() == std::io::ErrorKind::NotFound => continue,
+            Err(e) => return Err(e),
+        };
+
+        let size = file.metadata().await?.len();
+        let mut reader = tokio::io::BufReader::new(file).take(remaining);
+        let mut data: Vec<u8> = Vec::new();
+        reader.read_to_end(&mut data).await?;
+
+        if size > remaining {
+            tracing::warn!(
+                "Project doc `{}` exceeds remaining budget ({} bytes) - truncating.",
+                p.display(),
+                remaining,
+            );
+        }
+
+        let text = String::from_utf8_lossy(&data).to_string();
+        if !text.trim().is_empty() {
+            parts.push(text);
+            remaining = remaining.saturating_sub(data.len() as u64);
+        }
+    }
+
+    if parts.is_empty() {
+        Ok(None)
+    } else {
+        Ok(Some(parts.join("\n\n")))
+    }
+}
+
+/// Discover the list of AGENTS.md files using the same search rules as
+/// `read_project_docs`, but return the file paths instead of concatenated
+/// contents. The list is ordered from repository root to the current working
+/// directory (inclusive). Symlinks are allowed. When `project_doc_max_bytes`
+/// is zero, returns an empty list.
+pub fn discover_project_doc_paths(config: &Config) -> std::io::Result<Vec<PathBuf>> {
+    let mut dir = config.cwd.clone();
     if let Ok(canon) = dir.canonicalize() {
         dir = canon;
     }
 
-    while let Some(parent) = dir.parent() {
-        // `.git` can be a *file* (for worktrees or submodules) or a *dir*.
-        let git_marker = dir.join(".git");
-        let git_exists = match tokio::fs::metadata(&git_marker).await {
+    // Build chain from cwd upwards and detect git root.
+    let mut chain: Vec<PathBuf> = vec![dir.clone()];
+    let mut git_root: Option<PathBuf> = None;
+    let mut cursor = dir.clone();
+    while let Some(parent) = cursor.parent() {
+        let git_marker = cursor.join(".git");
+        let git_exists = match std::fs::metadata(&git_marker) {
             Ok(_) => true,
             Err(e) if e.kind() == std::io::ErrorKind::NotFound => false,
             Err(e) => return Err(e),
         };
 
         if git_exists {
-            // We are at the repo root – attempt one final load.
-            if let Some(doc) = load_first_candidate(&dir, CANDIDATE_FILENAMES, max_bytes).await? {
-                return Ok(Some(doc));
-            }
+            git_root = Some(cursor.clone());
             break;
         }
 
-        dir = parent.to_path_buf();
+        chain.push(parent.to_path_buf());
+        cursor = parent.to_path_buf();
     }
 
-    Ok(None)
-}
-
-/// Attempt to load the first candidate file found in `dir`. Returns the file
-/// contents (truncated if it exceeds `max_bytes`) when successful.
-async fn load_first_candidate(
-    dir: &Path,
-    names: &[&str],
-    max_bytes: usize,
-) -> std::io::Result<Option<String>> {
-    for name in names {
-        let candidate = dir.join(name);
-
-        let file = match tokio::fs::File::open(&candidate).await {
-            Err(e) if e.kind() == std::io::ErrorKind::NotFound => continue,
-            Err(e) => return Err(e),
-            Ok(f) => f,
-        };
-
-        let size = file.metadata().await?.len();
-
-        let reader = tokio::io::BufReader::new(file);
-        let mut data = Vec::with_capacity(std::cmp::min(size as usize, max_bytes));
-        let mut limited = reader.take(max_bytes as u64);
-        limited.read_to_end(&mut data).await?;
-
-        if size as usize > max_bytes {
-            tracing::warn!(
-                "Project doc `{}` exceeds {max_bytes} bytes - truncating.",
-                candidate.display(),
-            );
+    let search_dirs: Vec<PathBuf> = if let Some(root) = git_root {
+        let mut dirs: Vec<PathBuf> = Vec::new();
+        let mut saw_root = false;
+        for p in chain.iter().rev() {
+            if !saw_root {
+                if p == &root {
+                    saw_root = true;
+                } else {
+                    continue;
+                }
+            }
+            dirs.push(p.clone());
         }
+        dirs
+    } else {
+        vec![config.cwd.clone()]
+    };
 
-        let contents = String::from_utf8_lossy(&data).to_string();
-        if contents.trim().is_empty() {
-            // Empty file – treat as not found.
-            continue;
+    let mut found: Vec<PathBuf> = Vec::new();
+    for d in search_dirs {
+        for name in CANDIDATE_FILENAMES {
+            let candidate = d.join(name);
+            match std::fs::symlink_metadata(&candidate) {
+                Ok(md) => {
+                    let ft = md.file_type();
+                    // Allow regular files and symlinks; opening will later fail for dangling links.
+                    if ft.is_file() || ft.is_symlink() {
+                        found.push(candidate);
+                        break;
+                    }
+                }
+                Err(e) if e.kind() == std::io::ErrorKind::NotFound => continue,
+                Err(e) => return Err(e),
+            }
         }
-
-        return Ok(Some(contents));
     }
 
-    Ok(None)
+    Ok(found)
 }
 
 #[cfg(test)]
@@ -278,4 +319,32 @@ mod tests {
 
         assert_eq!(res, Some(INSTRUCTIONS.to_string()));
     }
+
+    /// When both the repository root and the working directory contain
+    /// AGENTS.md files, their contents are concatenated from root to cwd.
+    #[tokio::test]
+    async fn concatenates_root_and_cwd_docs() {
+        let repo = tempfile::tempdir().expect("tempdir");
+
+        // Simulate a git repository.
+        std::fs::write(
+            repo.path().join(".git"),
+            "gitdir: /path/to/actual/git/dir\n",
+        )
+        .unwrap();
+
+        // Repo root doc.
+        fs::write(repo.path().join("AGENTS.md"), "root doc").unwrap();
+
+        // Nested working directory with its own doc.
+        let nested = repo.path().join("workspace/crate_a");
+        std::fs::create_dir_all(&nested).unwrap();
+        fs::write(nested.join("AGENTS.md"), "crate doc").unwrap();
+
+        let mut cfg = make_config(&repo, 4096, None);
+        cfg.cwd = nested;
+
+        let res = get_user_instructions(&cfg).await.expect("doc expected");
+        assert_eq!(res, "root doc\n\ncrate doc");
+    }
 }

codex-rs/core/src/rollout.rs

@@ -22,7 +22,7 @@ use uuid::Uuid;
 use crate::config::Config;
 use crate::git_info::GitInfo;
 use crate::git_info::collect_git_info;
-use crate::models::ResponseItem;
+use codex_protocol::models::ResponseItem;
 
 const SESSIONS_SUBDIR: &str = "sessions";
 
@@ -132,6 +132,8 @@ impl RolloutRecorder {
                 | ResponseItem::LocalShellCall { .. }
                 | ResponseItem::FunctionCall { .. }
                 | ResponseItem::FunctionCallOutput { .. }
+                | ResponseItem::CustomToolCall { .. }
+                | ResponseItem::CustomToolCallOutput { .. }
                 | ResponseItem::Reasoning { .. } => filtered.push(item.clone()),
                 ResponseItem::Other => {
                     // These should never be serialized.
@@ -194,6 +196,8 @@ impl RolloutRecorder {
                     | ResponseItem::LocalShellCall { .. }
                     | ResponseItem::FunctionCall { .. }
                     | ResponseItem::FunctionCallOutput { .. }
+                    | ResponseItem::CustomToolCall { .. }
+                    | ResponseItem::CustomToolCallOutput { .. }
                     | ResponseItem::Reasoning { .. } => items.push(item),
                     ResponseItem::Other => {}
                 },
@@ -317,6 +321,8 @@ async fn rollout_writer(
                         | ResponseItem::LocalShellCall { .. }
                         | ResponseItem::FunctionCall { .. }
                         | ResponseItem::FunctionCallOutput { .. }
+                        | ResponseItem::CustomToolCall { .. }
+                        | ResponseItem::CustomToolCallOutput { .. }
                         | ResponseItem::Reasoning { .. } => {
                             writer.write_line(&item).await?;
                         }

codex-rs/core/src/safety.rs

@@ -21,7 +21,7 @@ pub enum SafetyCheck {
 pub fn assess_patch_safety(
     action: &ApplyPatchAction,
     policy: AskForApproval,
-    writable_roots: &[PathBuf],
+    sandbox_policy: &SandboxPolicy,
     cwd: &Path,
 ) -> SafetyCheck {
     if action.is_empty() {
@@ -45,7 +45,7 @@ pub fn assess_patch_safety(
     // is possible that paths in the patch are hard links to files outside the
     // writable roots, so we should still run `apply_patch` in a sandbox in that
     // case.
-    if is_write_patch_constrained_to_writable_paths(action, writable_roots, cwd)
+    if is_write_patch_constrained_to_writable_paths(action, sandbox_policy, cwd)
         || policy == AskForApproval::OnFailure
     {
         // Only auto‑approve when we can actually enforce a sandbox. Otherwise
@@ -171,13 +171,19 @@ pub fn get_platform_sandbox() -> Option<SandboxType> {
 
 fn is_write_patch_constrained_to_writable_paths(
     action: &ApplyPatchAction,
-    writable_roots: &[PathBuf],
+    sandbox_policy: &SandboxPolicy,
     cwd: &Path,
 ) -> bool {
     // Early‑exit if there are no declared writable roots.
-    if writable_roots.is_empty() {
-        return false;
-    }
+    let writable_roots = match sandbox_policy {
+        SandboxPolicy::ReadOnly => {
+            return false;
+        }
+        SandboxPolicy::DangerFullAccess => {
+            return true;
+        }
+        SandboxPolicy::WorkspaceWrite { .. } => sandbox_policy.get_writable_roots_with_cwd(cwd),
+    };
 
     // Normalize a path by removing `.` and resolving `..` without touching the
     // filesystem (works even if the file does not exist).
@@ -209,15 +215,9 @@ fn is_write_patch_constrained_to_writable_paths(
             None => return false,
         };
 
-        writable_roots.iter().any(|root| {
-            let root_abs = if root.is_absolute() {
-                root.clone()
-            } else {
-                normalize(&cwd.join(root)).unwrap_or_else(|| cwd.join(root))
-            };
-
-            abs.starts_with(&root_abs)
-        })
+        writable_roots
+            .iter()
+            .any(|writable_root| writable_root.is_path_writable(&abs))
     };
 
     for (path, change) in action.changes() {
@@ -231,10 +231,10 @@ fn is_write_patch_constrained_to_writable_paths(
                 if !is_path_writable(path) {
                     return false;
                 }
-                if let Some(dest) = move_path {
-                    if !is_path_writable(dest) {
-                        return false;
-                    }
+                if let Some(dest) = move_path
+                    && !is_path_writable(dest)
+                {
+                    return false;
                 }
             }
         }
@@ -246,38 +246,56 @@ fn is_write_patch_constrained_to_writable_paths(
 #[cfg(test)]
 mod tests {
     use super::*;
+    use tempfile::TempDir;
 
     #[test]
     fn test_writable_roots_constraint() {
-        let cwd = std::env::current_dir().unwrap();
+        // Use a temporary directory as our workspace to avoid touching
+        // the real current working directory.
+        let tmp = TempDir::new().unwrap();
+        let cwd = tmp.path().to_path_buf();
         let parent = cwd.parent().unwrap().to_path_buf();
 
-        // Helper to build a single‑entry map representing a patch that adds a
-        // file at `p`.
+        // Helper to build a single‑entry patch that adds a file at `p`.
         let make_add_change = |p: PathBuf| ApplyPatchAction::new_add_for_test(&p, "".to_string());
 
         let add_inside = make_add_change(cwd.join("inner.txt"));
         let add_outside = make_add_change(parent.join("outside.txt"));
 
+        // Policy limited to the workspace only; exclude system temp roots so
+        // only `cwd` is writable by default.
+        let policy_workspace_only = SandboxPolicy::WorkspaceWrite {
+            writable_roots: vec![],
+            network_access: false,
+            exclude_tmpdir_env_var: true,
+            exclude_slash_tmp: true,
+        };
+
         assert!(is_write_patch_constrained_to_writable_paths(
             &add_inside,
-            &[PathBuf::from(".")],
+            &policy_workspace_only,
             &cwd,
         ));
 
-        let add_outside_2 = make_add_change(parent.join("outside.txt"));
         assert!(!is_write_patch_constrained_to_writable_paths(
-            &add_outside_2,
-            &[PathBuf::from(".")],
+            &add_outside,
+            &policy_workspace_only,
             &cwd,
         ));
 
-        // With parent dir added as writable root, it should pass.
+        // With the parent dir explicitly added as a writable root, the
+        // outside write should be permitted.
+        let policy_with_parent = SandboxPolicy::WorkspaceWrite {
+            writable_roots: vec![parent.clone()],
+            network_access: false,
+            exclude_tmpdir_env_var: true,
+            exclude_slash_tmp: true,
+        };
         assert!(is_write_patch_constrained_to_writable_paths(
             &add_outside,
-            &[PathBuf::from("..")],
+            &policy_with_parent,
             &cwd,
-        ))
+        ));
     }
 
     #[test]

codex-rs/core/src/shell.rs

@@ -1,14 +1,24 @@
+use serde::Deserialize;
+use serde::Serialize;
 use shlex;
+use std::path::PathBuf;
 
-#[derive(Debug, PartialEq, Eq)]
+#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
 pub struct ZshShell {
     shell_path: String,
     zshrc_path: String,
 }
 
-#[derive(Debug, PartialEq, Eq)]
+#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
+pub struct PowerShellConfig {
+    exe: String, // Executable name or path, e.g. "pwsh" or "powershell.exe".
+    bash_exe_fallback: Option<PathBuf>, // In case the model generates a bash command.
+}
+
+#[derive(Debug, PartialEq, Eq, Clone, Serialize, Deserialize)]
 pub enum Shell {
     Zsh(ZshShell),
+    PowerShell(PowerShellConfig),
     Unknown,
 }
 
@@ -33,6 +43,61 @@ impl Shell {
                 }
                 Some(result)
             }
+            Shell::PowerShell(ps) => {
+                // If model generated a bash command, prefer a detected bash fallback
+                if let Some(script) = strip_bash_lc(&command) {
+                    return match &ps.bash_exe_fallback {
+                        Some(bash) => Some(vec![
+                            bash.to_string_lossy().to_string(),
+                            "-lc".to_string(),
+                            script,
+                        ]),
+
+                        // No bash fallback → run the script under PowerShell.
+                        // It will likely fail (except for some simple commands), but the error
+                        // should give a clue to the model to fix upon retry that it's running under PowerShell.
+                        None => Some(vec![
+                            ps.exe.clone(),
+                            "-NoProfile".to_string(),
+                            "-Command".to_string(),
+                            script,
+                        ]),
+                    };
+                }
+
+                // Not a bash command. If model did not generate a PowerShell command,
+                // turn it into a PowerShell command.
+                let first = command.first().map(String::as_str);
+                if first != Some(ps.exe.as_str()) {
+                    // TODO (CODEX_2900): Handle escaping newlines.
+                    if command.iter().any(|a| a.contains('\n') || a.contains('\r')) {
+                        return Some(command);
+                    }
+
+                    let joined = shlex::try_join(command.iter().map(|s| s.as_str())).ok();
+                    return joined.map(|arg| {
+                        vec![
+                            ps.exe.clone(),
+                            "-NoProfile".to_string(),
+                            "-Command".to_string(),
+                            arg,
+                        ]
+                    });
+                }
+
+                // Model generated a PowerShell command. Run it.
+                Some(command)
+            }
+            Shell::Unknown => None,
+        }
+    }
+
+    pub fn name(&self) -> Option<String> {
+        match self {
+            Shell::Zsh(zsh) => std::path::Path::new(&zsh.shell_path)
+                .file_name()
+                .map(|s| s.to_string_lossy().to_string()),
+            Shell::PowerShell(ps) => Some(ps.exe.clone()),
             Shell::Unknown => None,
         }
     }
@@ -70,13 +135,13 @@ pub async fn default_user_shell() -> Shell {
             }
             let stdout = String::from_utf8_lossy(&o.stdout);
             for line in stdout.lines() {
-                if let Some(shell_path) = line.strip_prefix("UserShell: ") {
-                    if shell_path.ends_with("/zsh") {
-                        return Shell::Zsh(ZshShell {
-                            shell_path: shell_path.to_string(),
-                            zshrc_path: format!("{home}/.zshrc"),
-                        });
-                    }
+                if let Some(shell_path) = line.strip_prefix("UserShell: ")
+                    && shell_path.ends_with("/zsh")
+                {
+                    return Shell::Zsh(ZshShell {
+                        shell_path: shell_path.to_string(),
+                        zshrc_path: format!("{home}/.zshrc"),
+                    });
                 }
             }
 
@@ -86,11 +151,51 @@ pub async fn default_user_shell() -> Shell {
     }
 }
 
-#[cfg(not(target_os = "macos"))]
+#[cfg(all(not(target_os = "macos"), not(target_os = "windows")))]
 pub async fn default_user_shell() -> Shell {
     Shell::Unknown
 }
 
+#[cfg(target_os = "windows")]
+pub async fn default_user_shell() -> Shell {
+    use tokio::process::Command;
+
+    // Prefer PowerShell 7+ (`pwsh`) if available, otherwise fall back to Windows PowerShell.
+    let has_pwsh = Command::new("pwsh")
+        .arg("-NoLogo")
+        .arg("-NoProfile")
+        .arg("-Command")
+        .arg("$PSVersionTable.PSVersion.Major")
+        .output()
+        .await
+        .map(|o| o.status.success())
+        .unwrap_or(false);
+    let bash_exe = if Command::new("bash.exe")
+        .arg("--version")
+        .output()
+        .await
+        .ok()
+        .map(|o| o.status.success())
+        .unwrap_or(false)
+    {
+        which::which("bash.exe").ok()
+    } else {
+        None
+    };
+
+    if has_pwsh {
+        Shell::PowerShell(PowerShellConfig {
+            exe: "pwsh.exe".to_string(),
+            bash_exe_fallback: bash_exe,
+        })
+    } else {
+        Shell::PowerShell(PowerShellConfig {
+            exe: "powershell.exe".to_string(),
+            bash_exe_fallback: bash_exe,
+        })
+    }
+}
+
 #[cfg(test)]
 #[cfg(target_os = "macos")]
 mod tests {
@@ -231,3 +336,97 @@ mod tests {
         }
     }
 }
+
+#[cfg(test)]
+#[cfg(target_os = "windows")]
+mod tests_windows {
+    use super::*;
+
+    #[test]
+    fn test_format_default_shell_invocation_powershell() {
+        let cases = vec![
+            (
+                Shell::PowerShell(PowerShellConfig {
+                    exe: "pwsh.exe".to_string(),
+                    bash_exe_fallback: None,
+                }),
+                vec!["bash", "-lc", "echo hello"],
+                vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
+            ),
+            (
+                Shell::PowerShell(PowerShellConfig {
+                    exe: "powershell.exe".to_string(),
+                    bash_exe_fallback: None,
+                }),
+                vec!["bash", "-lc", "echo hello"],
+                vec!["powershell.exe", "-NoProfile", "-Command", "echo hello"],
+            ),
+            (
+                Shell::PowerShell(PowerShellConfig {
+                    exe: "pwsh.exe".to_string(),
+                    bash_exe_fallback: Some(PathBuf::from("bash.exe")),
+                }),
+                vec!["bash", "-lc", "echo hello"],
+                vec!["bash.exe", "-lc", "echo hello"],
+            ),
+            (
+                Shell::PowerShell(PowerShellConfig {
+                    exe: "pwsh.exe".to_string(),
+                    bash_exe_fallback: Some(PathBuf::from("bash.exe")),
+                }),
+                vec![
+                    "bash",
+                    "-lc",
+                    "apply_patch <<'EOF'\n*** Begin Patch\n*** Update File: destination_file.txt\n-original content\n+modified content\n*** End Patch\nEOF",
+                ],
+                vec![
+                    "bash.exe",
+                    "-lc",
+                    "apply_patch <<'EOF'\n*** Begin Patch\n*** Update File: destination_file.txt\n-original content\n+modified content\n*** End Patch\nEOF",
+                ],
+            ),
+            (
+                Shell::PowerShell(PowerShellConfig {
+                    exe: "pwsh.exe".to_string(),
+                    bash_exe_fallback: Some(PathBuf::from("bash.exe")),
+                }),
+                vec!["echo", "hello"],
+                vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
+            ),
+            (
+                Shell::PowerShell(PowerShellConfig {
+                    exe: "pwsh.exe".to_string(),
+                    bash_exe_fallback: Some(PathBuf::from("bash.exe")),
+                }),
+                vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
+                vec!["pwsh.exe", "-NoProfile", "-Command", "echo hello"],
+            ),
+            (
+                // TODO (CODEX_2900): Handle escaping newlines for powershell invocation.
+                Shell::PowerShell(PowerShellConfig {
+                    exe: "powershell.exe".to_string(),
+                    bash_exe_fallback: Some(PathBuf::from("bash.exe")),
+                }),
+                vec![
+                    "codex-mcp-server.exe",
+                    "--codex-run-as-apply-patch",
+                    "*** Begin Patch\n*** Update File: C:\\Users\\person\\destination_file.txt\n-original content\n+modified content\n*** End Patch",
+                ],
+                vec![
+                    "codex-mcp-server.exe",
+                    "--codex-run-as-apply-patch",
+                    "*** Begin Patch\n*** Update File: C:\\Users\\person\\destination_file.txt\n-original content\n+modified content\n*** End Patch",
+                ],
+            ),
+        ];
+
+        for (shell, input, expected_cmd) in cases {
+            let actual_cmd = shell
+                .format_default_shell_invocation(input.iter().map(|s| s.to_string()).collect());
+            assert_eq!(
+                actual_cmd,
+                Some(expected_cmd.iter().map(|s| s.to_string()).collect())
+            );
+        }
+    }
+}

codex-rs/core/src/terminal.rs

@@ -0,0 +1,72 @@
+use std::sync::OnceLock;
+
+static TERMINAL: OnceLock<String> = OnceLock::new();
+
+pub fn user_agent() -> String {
+    TERMINAL.get_or_init(detect_terminal).to_string()
+}
+
+/// Sanitize a header value to be used in a User-Agent string.
+///
+/// This function replaces any characters that are not allowed in a User-Agent string with an underscore.
+///
+/// # Arguments
+///
+/// * `value` - The value to sanitize.
+fn is_valid_header_value_char(c: char) -> bool {
+    c.is_ascii_alphanumeric() || c == '-' || c == '_' || c == '.' || c == '/'
+}
+
+fn sanitize_header_value(value: String) -> String {
+    value.replace(|c| !is_valid_header_value_char(c), "_")
+}
+
+fn detect_terminal() -> String {
+    sanitize_header_value(
+        if let Ok(tp) = std::env::var("TERM_PROGRAM")
+            && !tp.trim().is_empty()
+        {
+            let ver = std::env::var("TERM_PROGRAM_VERSION").ok();
+            match ver {
+                Some(v) if !v.trim().is_empty() => format!("{tp}/{v}"),
+                _ => tp,
+            }
+        } else if let Ok(v) = std::env::var("WEZTERM_VERSION") {
+            if !v.trim().is_empty() {
+                format!("WezTerm/{v}")
+            } else {
+                "WezTerm".to_string()
+            }
+        } else if std::env::var("KITTY_WINDOW_ID").is_ok()
+            || std::env::var("TERM")
+                .map(|t| t.contains("kitty"))
+                .unwrap_or(false)
+        {
+            "kitty".to_string()
+        } else if std::env::var("ALACRITTY_SOCKET").is_ok()
+            || std::env::var("TERM")
+                .map(|t| t == "alacritty")
+                .unwrap_or(false)
+        {
+            "Alacritty".to_string()
+        } else if let Ok(v) = std::env::var("KONSOLE_VERSION") {
+            if !v.trim().is_empty() {
+                format!("Konsole/{v}")
+            } else {
+                "Konsole".to_string()
+            }
+        } else if std::env::var("GNOME_TERMINAL_SCREEN").is_ok() {
+            return "gnome-terminal".to_string();
+        } else if let Ok(v) = std::env::var("VTE_VERSION") {
+            if !v.trim().is_empty() {
+                format!("VTE/{v}")
+            } else {
+                "VTE".to_string()
+            }
+        } else if std::env::var("WT_SESSION").is_ok() {
+            return "WindowsTerminal".to_string();
+        } else {
+            std::env::var("TERM").unwrap_or_else(|_| "unknown".to_string())
+        },
+    )
+}

codex-rs/core/src/tool_apply_patch.rs

@@ -0,0 +1,145 @@
+use serde::Deserialize;
+use serde::Serialize;
+use std::collections::BTreeMap;
+
+use crate::openai_tools::FreeformTool;
+use crate::openai_tools::FreeformToolFormat;
+use crate::openai_tools::JsonSchema;
+use crate::openai_tools::OpenAiTool;
+use crate::openai_tools::ResponsesApiTool;
+
+#[derive(Serialize, Deserialize)]
+pub(crate) struct ApplyPatchToolArgs {
+    pub(crate) input: String,
+}
+
+#[derive(Debug, Clone, Serialize, Deserialize, PartialEq, Eq, Hash)]
+#[serde(rename_all = "snake_case")]
+pub enum ApplyPatchToolType {
+    Freeform,
+    Function,
+}
+
+/// Returns a custom tool that can be used to edit files. Well-suited for GPT-5 models
+/// https://platform.openai.com/docs/guides/function-calling#custom-tools
+pub(crate) fn create_apply_patch_freeform_tool() -> OpenAiTool {
+    OpenAiTool::Freeform(FreeformTool {
+        name: "apply_patch".to_string(),
+        description: "Use the `apply_patch` tool to edit files".to_string(),
+        format: FreeformToolFormat {
+            r#type: "grammar".to_string(),
+            syntax: "lark".to_string(),
+            definition: r#"start: begin_patch hunk+ end_patch
+begin_patch: "*** Begin Patch" LF
+end_patch: "*** End Patch" LF?
+
+hunk: add_hunk | delete_hunk | update_hunk
+add_hunk: "*** Add File: " filename LF add_line+
+delete_hunk: "*** Delete File: " filename LF
+update_hunk: "*** Update File: " filename LF change_move? change?
+
+filename: /(.+)/
+add_line: "+" /(.+)/ LF -> line
+
+change_move: "*** Move to: " filename LF
+change: (change_context | change_line)+ eof_line?
+change_context: ("@@" | "@@ " /(.+)/) LF
+change_line: ("+" | "-" | " ") /(.+)/ LF
+eof_line: "*** End of File" LF
+
+%import common.LF
+"#
+            .to_string(),
+        },
+    })
+}
+
+/// Returns a json tool that can be used to edit files. Should only be used with gpt-oss models
+pub(crate) fn create_apply_patch_json_tool() -> OpenAiTool {
+    let mut properties = BTreeMap::new();
+    properties.insert(
+        "input".to_string(),
+        JsonSchema::String {
+            description: Some(r#"The entire contents of the apply_patch command"#.to_string()),
+        },
+    );
+
+    OpenAiTool::Function(ResponsesApiTool {
+        name: "apply_patch".to_string(),
+        description: r#"Use the `apply_patch` tool to edit files.
+Your patch language is a stripped‑down, file‑oriented diff format designed to be easy to parse and safe to apply. You can think of it as a high‑level envelope:
+
+*** Begin Patch
+[ one or more file sections ]
+*** End Patch
+
+Within that envelope, you get a sequence of file operations.
+You MUST include a header to specify the action you are taking.
+Each operation starts with one of three headers:
+
+*** Add File: <path> - create a new file. Every following line is a + line (the initial contents).
+*** Delete File: <path> - remove an existing file. Nothing follows.
+*** Update File: <path> - patch an existing file in place (optionally with a rename).
+
+May be immediately followed by *** Move to: <new path> if you want to rename the file.
+Then one or more “hunks”, each introduced by @@ (optionally followed by a hunk header).
+Within a hunk each line starts with:
+
+For instructions on [context_before] and [context_after]:
+- By default, show 3 lines of code immediately above and 3 lines immediately below each change. If a change is within 3 lines of a previous change, do NOT duplicate the first change’s [context_after] lines in the second change’s [context_before] lines.
+- If 3 lines of context is insufficient to uniquely identify the snippet of code within the file, use the @@ operator to indicate the class or function to which the snippet belongs. For instance, we might have:
+@@ class BaseClass
+[3 lines of pre-context]
+- [old_code]
++ [new_code]
+[3 lines of post-context]
+
+- If a code block is repeated so many times in a class or function such that even a single `@@` statement and 3 lines of context cannot uniquely identify the snippet of code, you can use multiple `@@` statements to jump to the right context. For instance:
+
+@@ class BaseClass
+@@ 	 def method():
+[3 lines of pre-context]
+- [old_code]
++ [new_code]
+[3 lines of post-context]
+
+The full grammar definition is below:
+Patch := Begin { FileOp } End
+Begin := "*** Begin Patch" NEWLINE
+End := "*** End Patch" NEWLINE
+FileOp := AddFile | DeleteFile | UpdateFile
+AddFile := "*** Add File: " path NEWLINE { "+" line NEWLINE }
+DeleteFile := "*** Delete File: " path NEWLINE
+UpdateFile := "*** Update File: " path NEWLINE [ MoveTo ] { Hunk }
+MoveTo := "*** Move to: " newPath NEWLINE
+Hunk := "@@" [ header ] NEWLINE { HunkLine } [ "*** End of File" NEWLINE ]
+HunkLine := (" " | "-" | "+") text NEWLINE
+
+A full patch can combine several operations:
+
+*** Begin Patch
+*** Add File: hello.txt
++Hello world
+*** Update File: src/app.py
+*** Move to: src/main.py
+@@ def greet():
+-print("Hi")
++print("Hello, world!")
+*** Delete File: obsolete.txt
+*** End Patch
+
+It is important to remember:
+
+- You must include a header with your intended action (Add/Delete/Update)
+- You must prefix new lines with `+` even when creating a new file
+- File references can only be relative, NEVER ABSOLUTE.
+"#
+        .to_string(),
+        strict: false,
+        parameters: JsonSchema::Object {
+            properties,
+            required: Some(vec!["input".to_string()]),
+            additional_properties: Some(false),
+        },
+    })
+}

codex-rs/core/src/user_agent.rs

@@ -4,11 +4,12 @@ pub fn get_codex_user_agent(originator: Option<&str>) -> String {
     let build_version = env!("CARGO_PKG_VERSION");
     let os_info = os_info::get();
     format!(
-        "{}/{build_version} ({} {}; {})",
+        "{}/{build_version} ({} {}; {}) {}",
         originator.unwrap_or(DEFAULT_ORIGINATOR),
         os_info.os_type(),
         os_info.version(),
         os_info.architecture().unwrap_or("unknown"),
+        crate::terminal::user_agent()
     )
 }
 
@@ -27,9 +28,10 @@ mod tests {
     fn test_macos() {
         use regex_lite::Regex;
         let user_agent = get_codex_user_agent(None);
-        let re =
-            Regex::new(r"^codex_cli_rs/\d+\.\d+\.\d+ \(Mac OS \d+\.\d+\.\d+; (x86_64|arm64)\)$")
-                .unwrap();
+        let re = Regex::new(
+            r"^codex_cli_rs/\d+\.\d+\.\d+ \(Mac OS \d+\.\d+\.\d+; (x86_64|arm64)\) (\S+)$",
+        )
+        .unwrap();
         assert!(re.is_match(&user_agent));
     }
 }

codex-rs/core/tests/cli_stream.rs

@@ -297,13 +297,12 @@ async fn integration_creates_and_checks_session_file() {
                     Ok(v) => v,
                     Err(_) => continue,
                 };
-                if item.get("type").and_then(|t| t.as_str()) == Some("message") {
-                    if let Some(c) = item.get("content") {
-                        if c.to_string().contains(&marker) {
-                            matching_path = Some(path.to_path_buf());
-                            break;
-                        }
-                    }
+                if item.get("type").and_then(|t| t.as_str()) == Some("message")
+                    && let Some(c) = item.get("content")
+                    && c.to_string().contains(&marker)
+                {
+                    matching_path = Some(path.to_path_buf());
+                    break;
                 }
             }
         }
@@ -376,13 +375,12 @@ async fn integration_creates_and_checks_session_file() {
         let Ok(item) = serde_json::from_str::<serde_json::Value>(line) else {
             continue;
         };
-        if item.get("type").and_then(|t| t.as_str()) == Some("message") {
-            if let Some(c) = item.get("content") {
-                if c.to_string().contains(&marker) {
-                    found_message = true;
-                    break;
-                }
-            }
+        if item.get("type").and_then(|t| t.as_str()) == Some("message")
+            && let Some(c) = item.get("content")
+            && c.to_string().contains(&marker)
+        {
+            found_message = true;
+            break;
         }
     }
     assert!(

codex-rs/core/tests/client.rs

@@ -7,6 +7,7 @@ use codex_core::protocol::EventMsg;
 use codex_core::protocol::InputItem;
 use codex_core::protocol::Op;
 use codex_core::spawn::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
+use codex_login::AuthMode;
 use codex_login::CodexAuth;
 use core_test_support::load_default_config_for_test;
 use core_test_support::load_sse_fixture_with_id;
@@ -54,6 +55,59 @@ fn assert_message_ends_with(request_body: &serde_json::Value, text: &str) {
     );
 }
 
+/// Writes an `auth.json` into the provided `codex_home` with the specified parameters.
+/// Returns the fake JWT string written to `tokens.id_token`.
+#[expect(clippy::unwrap_used)]
+fn write_auth_json(
+    codex_home: &TempDir,
+    openai_api_key: Option<&str>,
+    chatgpt_plan_type: &str,
+    access_token: &str,
+    account_id: Option<&str>,
+) -> String {
+    use base64::Engine as _;
+    use serde_json::json;
+
+    let header = json!({ "alg": "none", "typ": "JWT" });
+    let payload = json!({
+        "email": "user@example.com",
+        "https://api.openai.com/auth": {
+            "chatgpt_plan_type": chatgpt_plan_type,
+            "chatgpt_account_id": account_id.unwrap_or("acc-123")
+        }
+    });
+
+    let b64 = |b: &[u8]| base64::engine::general_purpose::URL_SAFE_NO_PAD.encode(b);
+    let header_b64 = b64(&serde_json::to_vec(&header).unwrap());
+    let payload_b64 = b64(&serde_json::to_vec(&payload).unwrap());
+    let signature_b64 = b64(b"sig");
+    let fake_jwt = format!("{header_b64}.{payload_b64}.{signature_b64}");
+
+    let mut tokens = json!({
+        "id_token": fake_jwt,
+        "access_token": access_token,
+        "refresh_token": "refresh-test",
+    });
+    if let Some(acc) = account_id {
+        tokens["account_id"] = json!(acc);
+    }
+
+    let auth_json = json!({
+        "OPENAI_API_KEY": openai_api_key,
+        "tokens": tokens,
+        // RFC3339 datetime; value doesn't matter for these tests
+        "last_refresh": "2025-08-06T20:41:36.232376Z",
+    });
+
+    std::fs::write(
+        codex_home.path().join("auth.json"),
+        serde_json::to_string_pretty(&auth_json).unwrap(),
+    )
+    .unwrap();
+
+    fake_jwt
+}
+
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn includes_session_id_and_model_headers_in_request() {
     if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
@@ -88,13 +142,14 @@ async fn includes_session_id_and_model_headers_in_request() {
     let mut config = load_default_config_for_test(&codex_home);
     config.model_provider = model_provider;
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
     let NewConversation {
         conversation: codex,
         conversation_id,
         session_configured: _,
     } = conversation_manager
-        .new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
+        .new_conversation(config)
         .await
         .expect("create new conversation");
 
@@ -153,9 +208,10 @@ async fn includes_base_instructions_override_in_request() {
     config.base_instructions = Some("test instructions".to_string());
     config.model_provider = model_provider;
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
     let codex = conversation_manager
-        .new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
+        .new_conversation(config)
         .await
         .expect("create new conversation")
         .conversation;
@@ -206,11 +262,12 @@ async fn originator_config_override_is_used() {
     let codex_home = TempDir::new().unwrap();
     let mut config = load_default_config_for_test(&codex_home);
     config.model_provider = model_provider;
-    config.internal_originator = Some("my_override".to_string());
+    config.responses_originator_header = "my_override".to_owned();
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
     let codex = conversation_manager
-        .new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
+        .new_conversation(config)
         .await
         .expect("create new conversation")
         .conversation;
@@ -264,13 +321,13 @@ async fn chatgpt_auth_sends_correct_request() {
     let codex_home = TempDir::new().unwrap();
     let mut config = load_default_config_for_test(&codex_home);
     config.model_provider = model_provider;
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager = ConversationManager::with_auth(create_dummy_codex_auth());
     let NewConversation {
         conversation: codex,
         conversation_id,
         session_configured: _,
     } = conversation_manager
-        .new_conversation_with_auth(config, Some(create_dummy_codex_auth()))
+        .new_conversation(config)
         .await
         .expect("create new conversation");
 
@@ -311,6 +368,168 @@ async fn chatgpt_auth_sends_correct_request() {
     );
 }
 
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn prefers_chatgpt_token_when_config_prefers_chatgpt() {
+    if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
+        println!(
+            "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
+        );
+        return;
+    }
+
+    // Mock server
+    let server = MockServer::start().await;
+
+    let first = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(sse_completed("resp1"), "text/event-stream");
+
+    // Expect ChatGPT base path and correct headers
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .and(header_regex("Authorization", r"Bearer Access-123"))
+        .and(header_regex("chatgpt-account-id", r"acc-123"))
+        .respond_with(first)
+        .expect(1)
+        .mount(&server)
+        .await;
+
+    let model_provider = ModelProviderInfo {
+        base_url: Some(format!("{}/v1", server.uri())),
+        ..built_in_model_providers()["openai"].clone()
+    };
+
+    // Init session
+    let codex_home = TempDir::new().unwrap();
+    // Write auth.json that contains both API key and ChatGPT tokens for a plan that should prefer ChatGPT.
+    let _jwt = write_auth_json(
+        &codex_home,
+        Some("sk-test-key"),
+        "pro",
+        "Access-123",
+        Some("acc-123"),
+    );
+
+    let mut config = load_default_config_for_test(&codex_home);
+    config.model_provider = model_provider;
+    config.preferred_auth_method = AuthMode::ChatGPT;
+
+    let auth_manager =
+        match CodexAuth::from_codex_home(codex_home.path(), config.preferred_auth_method) {
+            Ok(Some(auth)) => codex_login::AuthManager::from_auth_for_testing(auth),
+            Ok(None) => panic!("No CodexAuth found in codex_home"),
+            Err(e) => panic!("Failed to load CodexAuth: {}", e),
+        };
+    let conversation_manager = ConversationManager::new(auth_manager);
+    let NewConversation {
+        conversation: codex,
+        ..
+    } = conversation_manager
+        .new_conversation(config)
+        .await
+        .expect("create new conversation");
+
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello".into(),
+            }],
+        })
+        .await
+        .unwrap();
+
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // verify request body flags
+    let request = &server.received_requests().await.unwrap()[0];
+    let request_body = request.body_json::<serde_json::Value>().unwrap();
+    assert!(
+        !request_body["store"].as_bool().unwrap(),
+        "store should be false for ChatGPT auth"
+    );
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn prefers_apikey_when_config_prefers_apikey_even_with_chatgpt_tokens() {
+    if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
+        println!(
+            "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
+        );
+        return;
+    }
+
+    // Mock server
+    let server = MockServer::start().await;
+
+    let first = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(sse_completed("resp1"), "text/event-stream");
+
+    // Expect API key header, no ChatGPT account header required.
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .and(header_regex("Authorization", r"Bearer sk-test-key"))
+        .respond_with(first)
+        .expect(1)
+        .mount(&server)
+        .await;
+
+    let model_provider = ModelProviderInfo {
+        base_url: Some(format!("{}/v1", server.uri())),
+        ..built_in_model_providers()["openai"].clone()
+    };
+
+    // Init session
+    let codex_home = TempDir::new().unwrap();
+    // Write auth.json that contains both API key and ChatGPT tokens for a plan that should prefer ChatGPT,
+    // but config will force API key preference.
+    let _jwt = write_auth_json(
+        &codex_home,
+        Some("sk-test-key"),
+        "pro",
+        "Access-123",
+        Some("acc-123"),
+    );
+
+    let mut config = load_default_config_for_test(&codex_home);
+    config.model_provider = model_provider;
+    config.preferred_auth_method = AuthMode::ApiKey;
+
+    let auth_manager =
+        match CodexAuth::from_codex_home(codex_home.path(), config.preferred_auth_method) {
+            Ok(Some(auth)) => codex_login::AuthManager::from_auth_for_testing(auth),
+            Ok(None) => panic!("No CodexAuth found in codex_home"),
+            Err(e) => panic!("Failed to load CodexAuth: {}", e),
+        };
+    let conversation_manager = ConversationManager::new(auth_manager);
+    let NewConversation {
+        conversation: codex,
+        ..
+    } = conversation_manager
+        .new_conversation(config)
+        .await
+        .expect("create new conversation");
+
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello".into(),
+            }],
+        })
+        .await
+        .unwrap();
+
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // verify request body flags
+    let request = &server.received_requests().await.unwrap()[0];
+    let request_body = request.body_json::<serde_json::Value>().unwrap();
+    assert!(
+        request_body["store"].as_bool().unwrap(),
+        "store should be true for API key auth"
+    );
+}
+
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn includes_user_instructions_message_in_request() {
     let server = MockServer::start().await;
@@ -336,9 +555,10 @@ async fn includes_user_instructions_message_in_request() {
     config.model_provider = model_provider;
     config.user_instructions = Some("be nice".to_string());
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
     let codex = conversation_manager
-        .new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
+        .new_conversation(config)
         .await
         .expect("create new conversation")
         .conversation;
@@ -428,9 +648,9 @@ async fn azure_overrides_assign_properties_used_for_responses_url() {
     let mut config = load_default_config_for_test(&codex_home);
     config.model_provider = provider;
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager = ConversationManager::with_auth(create_dummy_codex_auth());
     let codex = conversation_manager
-        .new_conversation_with_auth(config, None)
+        .new_conversation(config)
         .await
         .expect("create new conversation")
         .conversation;
@@ -504,9 +724,9 @@ async fn env_var_overrides_loaded_auth() {
     let mut config = load_default_config_for_test(&codex_home);
     config.model_provider = provider;
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager = ConversationManager::with_auth(create_dummy_codex_auth());
     let codex = conversation_manager
-        .new_conversation_with_auth(config, Some(create_dummy_codex_auth()))
+        .new_conversation(config)
         .await
         .expect("create new conversation")
         .conversation;

codex-rs/core/tests/common/lib.rs

@@ -47,6 +47,26 @@ pub fn load_sse_fixture(path: impl AsRef<std::path::Path>) -> String {
         .collect()
 }
 
+pub fn load_sse_fixture_with_id_from_str(raw: &str, id: &str) -> String {
+    let replaced = raw.replace("__ID__", id);
+    let events: Vec<serde_json::Value> =
+        serde_json::from_str(&replaced).expect("parse JSON fixture");
+    events
+        .into_iter()
+        .map(|e| {
+            let kind = e
+                .get("type")
+                .and_then(|v| v.as_str())
+                .expect("fixture event missing type");
+            if e.as_object().map(|o| o.len() == 1).unwrap_or(false) {
+                format!("event: {kind}\n\n")
+            } else {
+                format!("event: {kind}\ndata: {e}\n\n")
+            }
+        })
+        .collect()
+}
+
 /// Same as [`load_sse_fixture`], but replaces the placeholder `__ID__` in the
 /// fixture template with the supplied identifier before parsing. This lets a
 /// single JSON template be reused by multiple tests that each need a unique

codex-rs/core/tests/compact.rs

@@ -141,9 +141,9 @@ async fn summarize_context_three_requests_and_instructions() {
     let home = TempDir::new().unwrap();
     let mut config = load_default_config_for_test(&home);
     config.model_provider = model_provider;
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager = ConversationManager::with_auth(CodexAuth::from_api_key("dummy"));
     let codex = conversation_manager
-        .new_conversation_with_auth(config, Some(CodexAuth::from_api_key("dummy")))
+        .new_conversation(config)
         .await
         .unwrap()
         .conversation;

codex-rs/core/tests/prompt_caching.rs

@@ -1,9 +1,17 @@
+#![allow(clippy::unwrap_used)]
+
 use codex_core::ConversationManager;
 use codex_core::ModelProviderInfo;
 use codex_core::built_in_model_providers;
+use codex_core::model_family::find_family_for_model;
+use codex_core::protocol::AskForApproval;
 use codex_core::protocol::EventMsg;
 use codex_core::protocol::InputItem;
 use codex_core::protocol::Op;
+use codex_core::protocol::SandboxPolicy;
+use codex_core::protocol_config_types::ReasoningEffort;
+use codex_core::protocol_config_types::ReasoningSummary;
+use codex_core::shell::default_user_shell;
 use codex_login::CodexAuth;
 use core_test_support::load_default_config_for_test;
 use core_test_support::load_sse_fixture_with_id;
@@ -20,6 +28,185 @@ fn sse_completed(id: &str) -> String {
     load_sse_fixture_with_id("tests/fixtures/completed_template.json", id)
 }
 
+fn assert_tool_names(body: &serde_json::Value, expected_names: &[&str]) {
+    assert_eq!(
+        body["tools"]
+            .as_array()
+            .unwrap()
+            .iter()
+            .map(|t| t["name"].as_str().unwrap().to_string())
+            .collect::<Vec<_>>(),
+        expected_names
+    );
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+async fn codex_mini_latest_tools() {
+    use pretty_assertions::assert_eq;
+
+    let server = MockServer::start().await;
+
+    let sse = sse_completed("resp");
+    let template = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(sse, "text/event-stream");
+
+    // Expect two POSTs to /v1/responses
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(template)
+        .expect(2)
+        .mount(&server)
+        .await;
+
+    let model_provider = ModelProviderInfo {
+        base_url: Some(format!("{}/v1", server.uri())),
+        ..built_in_model_providers()["openai"].clone()
+    };
+
+    let cwd = TempDir::new().unwrap();
+    let codex_home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&codex_home);
+    config.cwd = cwd.path().to_path_buf();
+    config.model_provider = model_provider;
+    config.user_instructions = Some("be consistent and helpful".to_string());
+
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
+    config.include_apply_patch_tool = false;
+    config.model = "codex-mini-latest".to_string();
+    config.model_family = find_family_for_model("codex-mini-latest").unwrap();
+
+    let codex = conversation_manager
+        .new_conversation(config)
+        .await
+        .expect("create new conversation")
+        .conversation;
+
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello 1".into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello 2".into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    let requests = server.received_requests().await.unwrap();
+    assert_eq!(requests.len(), 2, "expected two POST requests");
+
+    let expected_instructions = [
+        include_str!("../prompt.md"),
+        include_str!("../../apply-patch/apply_patch_tool_instructions.md"),
+    ]
+    .join("\n");
+
+    let body0 = requests[0].body_json::<serde_json::Value>().unwrap();
+    assert_eq!(
+        body0["instructions"],
+        serde_json::json!(expected_instructions),
+    );
+    let body1 = requests[1].body_json::<serde_json::Value>().unwrap();
+    assert_eq!(
+        body1["instructions"],
+        serde_json::json!(expected_instructions),
+    );
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
+async fn prompt_tools_are_consistent_across_requests() {
+    use pretty_assertions::assert_eq;
+
+    let server = MockServer::start().await;
+
+    let sse = sse_completed("resp");
+    let template = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(sse, "text/event-stream");
+
+    // Expect two POSTs to /v1/responses
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(template)
+        .expect(2)
+        .mount(&server)
+        .await;
+
+    let model_provider = ModelProviderInfo {
+        base_url: Some(format!("{}/v1", server.uri())),
+        ..built_in_model_providers()["openai"].clone()
+    };
+
+    let cwd = TempDir::new().unwrap();
+    let codex_home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&codex_home);
+    config.cwd = cwd.path().to_path_buf();
+    config.model_provider = model_provider;
+    config.user_instructions = Some("be consistent and helpful".to_string());
+    config.include_apply_patch_tool = true;
+    config.include_plan_tool = true;
+
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
+    let codex = conversation_manager
+        .new_conversation(config)
+        .await
+        .expect("create new conversation")
+        .conversation;
+
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello 1".into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello 2".into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    let requests = server.received_requests().await.unwrap();
+    assert_eq!(requests.len(), 2, "expected two POST requests");
+
+    let expected_instructions: &str = include_str!("../prompt.md");
+    // our internal implementation is responsible for keeping tools in sync
+    // with the OpenAI schema, so we just verify the tool presence here
+    let expected_tools_names: &[&str] = &["shell", "update_plan", "apply_patch"];
+    let body0 = requests[0].body_json::<serde_json::Value>().unwrap();
+    assert_eq!(
+        body0["instructions"],
+        serde_json::json!(expected_instructions),
+    );
+    assert_tool_names(&body0, expected_tools_names);
+
+    let body1 = requests[1].body_json::<serde_json::Value>().unwrap();
+    assert_eq!(
+        body1["instructions"],
+        serde_json::json!(expected_instructions),
+    );
+    assert_tool_names(&body1, expected_tools_names);
+}
+
 #[tokio::test(flavor = "multi_thread", worker_threads = 2)]
 async fn prefixes_context_and_instructions_once_and_consistently_across_requests() {
     use pretty_assertions::assert_eq;
@@ -51,9 +238,10 @@ async fn prefixes_context_and_instructions_once_and_consistently_across_requests
     config.model_provider = model_provider;
     config.user_instructions = Some("be consistent and helpful".to_string());
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
     let codex = conversation_manager
-        .new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
+        .new_conversation(config)
         .await
         .expect("create new conversation")
         .conversation;
@@ -81,9 +269,20 @@ async fn prefixes_context_and_instructions_once_and_consistently_across_requests
     let requests = server.received_requests().await.unwrap();
     assert_eq!(requests.len(), 2, "expected two POST requests");
 
+    let shell = default_user_shell().await;
+
     let expected_env_text = format!(
-        "<environment_context>\nCurrent working directory: {}\nApproval policy: on-request\nSandbox mode: read-only\nNetwork access: restricted\n</environment_context>",
-        cwd.path().to_string_lossy()
+        r#"<environment_context>
+  <cwd>{}</cwd>
+  <approval_policy>on-request</approval_policy>
+  <sandbox_mode>read-only</sandbox_mode>
+  <network_access>restricted</network_access>
+{}</environment_context>"#,
+        cwd.path().to_string_lossy(),
+        match shell.name() {
+            Some(name) => format!("  <shell>{}</shell>\n", name),
+            None => String::new(),
+        }
     );
     let expected_ui_text =
         "<user_instructions>\n\nbe consistent and helpful\n\n</user_instructions>";
@@ -129,3 +328,231 @@ async fn prefixes_context_and_instructions_once_and_consistently_across_requests
     );
     assert_eq!(body2["input"], expected_body2);
 }
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn overrides_turn_context_but_keeps_cached_prefix_and_key_constant() {
+    use pretty_assertions::assert_eq;
+
+    let server = MockServer::start().await;
+
+    let sse = sse_completed("resp");
+    let template = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(sse, "text/event-stream");
+
+    // Expect two POSTs to /v1/responses
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(template)
+        .expect(2)
+        .mount(&server)
+        .await;
+
+    let model_provider = ModelProviderInfo {
+        base_url: Some(format!("{}/v1", server.uri())),
+        ..built_in_model_providers()["openai"].clone()
+    };
+
+    let cwd = TempDir::new().unwrap();
+    let codex_home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&codex_home);
+    config.cwd = cwd.path().to_path_buf();
+    config.model_provider = model_provider;
+    config.user_instructions = Some("be consistent and helpful".to_string());
+
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
+    let codex = conversation_manager
+        .new_conversation(config)
+        .await
+        .expect("create new conversation")
+        .conversation;
+
+    // First turn
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello 1".into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    let writable = TempDir::new().unwrap();
+    codex
+        .submit(Op::OverrideTurnContext {
+            cwd: None,
+            approval_policy: Some(AskForApproval::Never),
+            sandbox_policy: Some(SandboxPolicy::WorkspaceWrite {
+                writable_roots: vec![writable.path().to_path_buf()],
+                network_access: true,
+                exclude_tmpdir_env_var: true,
+                exclude_slash_tmp: true,
+            }),
+            model: Some("o3".to_string()),
+            effort: Some(ReasoningEffort::High),
+            summary: Some(ReasoningSummary::Detailed),
+        })
+        .await
+        .unwrap();
+
+    // Second turn after overrides
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello 2".into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // Verify we issued exactly two requests, and the cached prefix stayed identical.
+    let requests = server.received_requests().await.unwrap();
+    assert_eq!(requests.len(), 2, "expected two POST requests");
+
+    let body1 = requests[0].body_json::<serde_json::Value>().unwrap();
+    let body2 = requests[1].body_json::<serde_json::Value>().unwrap();
+    // prompt_cache_key should remain constant across overrides
+    assert_eq!(
+        body1["prompt_cache_key"], body2["prompt_cache_key"],
+        "prompt_cache_key should not change across overrides"
+    );
+
+    // The entire prefix from the first request should be identical and reused
+    // as the prefix of the second request, ensuring cache hit potential.
+    let expected_user_message_2 = serde_json::json!({
+        "type": "message",
+        "id": serde_json::Value::Null,
+        "role": "user",
+        "content": [ { "type": "input_text", "text": "hello 2" } ]
+    });
+    // After overriding the turn context, the environment context should be emitted again
+    // reflecting the new approval policy and sandbox settings. Omit cwd because it did
+    // not change.
+    let expected_env_text_2 = r#"<environment_context>
+  <approval_policy>never</approval_policy>
+  <sandbox_mode>workspace-write</sandbox_mode>
+  <network_access>enabled</network_access>
+</environment_context>"#;
+    let expected_env_msg_2 = serde_json::json!({
+        "type": "message",
+        "id": serde_json::Value::Null,
+        "role": "user",
+        "content": [ { "type": "input_text", "text": expected_env_text_2 } ]
+    });
+    let expected_body2 = serde_json::json!(
+        [
+            body1["input"].as_array().unwrap().as_slice(),
+            [expected_env_msg_2, expected_user_message_2].as_slice(),
+        ]
+        .concat()
+    );
+    assert_eq!(body2["input"], expected_body2);
+}
+
+#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
+async fn per_turn_overrides_keep_cached_prefix_and_key_constant() {
+    use pretty_assertions::assert_eq;
+
+    let server = MockServer::start().await;
+
+    let sse = sse_completed("resp");
+    let template = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(sse, "text/event-stream");
+
+    // Expect two POSTs to /v1/responses
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(template)
+        .expect(2)
+        .mount(&server)
+        .await;
+
+    let model_provider = ModelProviderInfo {
+        base_url: Some(format!("{}/v1", server.uri())),
+        ..built_in_model_providers()["openai"].clone()
+    };
+
+    let cwd = TempDir::new().unwrap();
+    let codex_home = TempDir::new().unwrap();
+    let mut config = load_default_config_for_test(&codex_home);
+    config.cwd = cwd.path().to_path_buf();
+    config.model_provider = model_provider;
+    config.user_instructions = Some("be consistent and helpful".to_string());
+
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
+    let codex = conversation_manager
+        .new_conversation(config)
+        .await
+        .expect("create new conversation")
+        .conversation;
+
+    // First turn
+    codex
+        .submit(Op::UserInput {
+            items: vec![InputItem::Text {
+                text: "hello 1".into(),
+            }],
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // Second turn using per-turn overrides via UserTurn
+    let new_cwd = TempDir::new().unwrap();
+    let writable = TempDir::new().unwrap();
+    codex
+        .submit(Op::UserTurn {
+            items: vec![InputItem::Text {
+                text: "hello 2".into(),
+            }],
+            cwd: new_cwd.path().to_path_buf(),
+            approval_policy: AskForApproval::Never,
+            sandbox_policy: SandboxPolicy::WorkspaceWrite {
+                writable_roots: vec![writable.path().to_path_buf()],
+                network_access: true,
+                exclude_tmpdir_env_var: true,
+                exclude_slash_tmp: true,
+            },
+            model: "o3".to_string(),
+            effort: ReasoningEffort::High,
+            summary: ReasoningSummary::Detailed,
+        })
+        .await
+        .unwrap();
+    wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
+
+    // Verify we issued exactly two requests, and the cached prefix stayed identical.
+    let requests = server.received_requests().await.unwrap();
+    assert_eq!(requests.len(), 2, "expected two POST requests");
+
+    let body1 = requests[0].body_json::<serde_json::Value>().unwrap();
+    let body2 = requests[1].body_json::<serde_json::Value>().unwrap();
+
+    // prompt_cache_key should remain constant across per-turn overrides
+    assert_eq!(
+        body1["prompt_cache_key"], body2["prompt_cache_key"],
+        "prompt_cache_key should not change across per-turn overrides"
+    );
+
+    // The entire prefix from the first request should be identical and reused
+    // as the prefix of the second request.
+    let expected_user_message_2 = serde_json::json!({
+        "type": "message",
+        "id": serde_json::Value::Null,
+        "role": "user",
+        "content": [ { "type": "input_text", "text": "hello 2" } ]
+    });
+    let expected_body2 = serde_json::json!(
+        [
+            body1["input"].as_array().unwrap().as_slice(),
+            [expected_user_message_2].as_slice(),
+        ]
+        .concat()
+    );
+    assert_eq!(body2["input"], expected_body2);
+}

codex-rs/core/tests/stream_error_allows_next_turn.rs

@@ -88,9 +88,10 @@ async fn continue_after_stream_error() {
     config.base_instructions = Some("You are a helpful assistant".to_string());
     config.model_provider = provider;
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
     let codex = conversation_manager
-        .new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
+        .new_conversation(config)
         .await
         .unwrap()
         .conversation;

codex-rs/core/tests/stream_no_completed.rs

@@ -93,9 +93,10 @@ async fn retries_on_early_close() {
     let codex_home = TempDir::new().unwrap();
     let mut config = load_default_config_for_test(&codex_home);
     config.model_provider = model_provider;
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager =
+        ConversationManager::with_auth(CodexAuth::from_api_key("Test API Key"));
     let codex = conversation_manager
-        .new_conversation_with_auth(config, Some(CodexAuth::from_api_key("Test API Key")))
+        .new_conversation(config)
         .await
         .unwrap()
         .conversation;

codex-rs/exec/Cargo.toml

@@ -25,7 +25,9 @@ codex-common = { path = "../common", features = [
     "sandbox_summary",
 ] }
 codex-core = { path = "../core" }
+codex-login = { path = "../login" }
 codex-ollama = { path = "../ollama" }
+codex-protocol = { path = "../protocol" }
 owo-colors = "4.2.0"
 serde_json = "1"
 shlex = "1.3.0"
@@ -41,6 +43,8 @@ tracing-subscriber = { version = "0.3.19", features = ["env-filter"] }
 
 [dev-dependencies]
 assert_cmd = "2"
+core_test_support = { path = "../core/tests/common" }
 libc = "0.2"
 predicates = "3"
 tempfile = "3.13.0"
+wiremock = "0.6"

codex-rs/exec/src/event_processor.rs

@@ -29,9 +29,9 @@ pub(crate) fn handle_last_message(last_agent_message: Option<&str>, output_file:
 }
 
 fn write_last_message_file(contents: &str, last_message_path: Option<&Path>) {
-    if let Some(path) = last_message_path {
-        if let Err(e) = std::fs::write(path, contents) {
-            eprintln!("Failed to write last message file {path:?}: {e}");
-        }
+    if let Some(path) = last_message_path
+        && let Err(e) = std::fs::write(path, contents)
+    {
+        eprintln!("Failed to write last message file {path:?}: {e}");
     }
 }

codex-rs/exec/src/event_processor_with_human_output.rs

@@ -20,7 +20,9 @@ use codex_core::protocol::McpToolCallEndEvent;
 use codex_core::protocol::PatchApplyBeginEvent;
 use codex_core::protocol::PatchApplyEndEvent;
 use codex_core::protocol::SessionConfiguredEvent;
+use codex_core::protocol::StreamErrorEvent;
 use codex_core::protocol::TaskCompleteEvent;
+use codex_core::protocol::TurnAbortReason;
 use codex_core::protocol::TurnDiffEvent;
 use owo_colors::OwoColorize;
 use owo_colors::Style;
@@ -173,6 +175,9 @@ impl EventProcessor for EventProcessorWithHumanOutput {
             EventMsg::BackgroundEvent(BackgroundEventEvent { message }) => {
                 ts_println!(self, "{}", message.style(self.dimmed));
             }
+            EventMsg::StreamError(StreamErrorEvent { message }) => {
+                ts_println!(self, "{}", message.style(self.dimmed));
+            }
             EventMsg::TaskStarted => {
                 // Ignore.
             }
@@ -286,6 +291,7 @@ impl EventProcessor for EventProcessorWithHumanOutput {
                 stderr,
                 duration,
                 exit_code,
+                ..
             }) => {
                 let exec_command = self.call_id_to_command.remove(&call_id);
                 let (duration, call) = if let Some(ExecCommandBegin { command, .. }) = exec_command
@@ -522,7 +528,19 @@ impl EventProcessor for EventProcessorWithHumanOutput {
             EventMsg::GetHistoryEntryResponse(_) => {
                 // Currently ignored in exec output.
             }
+            EventMsg::McpListToolsResponse(_) => {
+                // Currently ignored in exec output.
+            }
+            EventMsg::TurnAborted(abort_reason) => match abort_reason.reason {
+                TurnAbortReason::Interrupted => {
+                    ts_println!(self, "task interrupted");
+                }
+                TurnAbortReason::Replaced => {
+                    ts_println!(self, "task aborted: replaced by a new task");
+                }
+            },
             EventMsg::ShutdownComplete => return CodexStatus::Shutdown,
+            EventMsg::ConversationHistory(_) => {}
         }
         CodexStatus::Running
     }

codex-rs/exec/src/lib.rs

@@ -13,7 +13,6 @@ use codex_core::ConversationManager;
 use codex_core::NewConversation;
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
-use codex_core::config_types::SandboxMode;
 use codex_core::protocol::AskForApproval;
 use codex_core::protocol::Event;
 use codex_core::protocol::EventMsg;
@@ -21,7 +20,9 @@ use codex_core::protocol::InputItem;
 use codex_core::protocol::Op;
 use codex_core::protocol::TaskCompleteEvent;
 use codex_core::util::is_inside_git_repo;
+use codex_login::AuthManager;
 use codex_ollama::DEFAULT_OSS_MODEL;
+use codex_protocol::config_types::SandboxMode;
 use event_processor_with_human_output::EventProcessorWithHumanOutput;
 use event_processor_with_json_output::EventProcessorWithJsonOutput;
 use tracing::debug;
@@ -146,6 +147,7 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
         codex_linux_sandbox_exe,
         base_instructions: None,
         include_plan_tool: None,
+        include_apply_patch_tool: None,
         disable_response_storage: oss.then_some(true),
         show_raw_agent_reasoning: oss.then_some(true),
     };
@@ -184,7 +186,10 @@ pub async fn run_main(cli: Cli, codex_linux_sandbox_exe: Option<PathBuf>) -> any
         std::process::exit(1);
     }
 
-    let conversation_manager = ConversationManager::default();
+    let conversation_manager = ConversationManager::new(AuthManager::shared(
+        config.codex_home.clone(),
+        config.preferred_auth_method,
+    ));
     let NewConversation {
         conversation_id: _,
         conversation,

codex-rs/exec/tests/apply_patch.rs

@@ -1,3 +1,5 @@
+#![allow(clippy::expect_used, clippy::unwrap_used)]
+
 use anyhow::Context;
 use assert_cmd::prelude::*;
 use codex_core::CODEX_APPLY_PATCH_ARG1;
@@ -37,3 +39,301 @@ fn test_standalone_exec_cli_can_use_apply_patch() -> anyhow::Result<()> {
     );
     Ok(())
 }
+
+#[cfg(not(target_os = "windows"))]
+#[tokio::test]
+async fn test_apply_patch_tool() -> anyhow::Result<()> {
+    use core_test_support::load_sse_fixture_with_id_from_str;
+    use tempfile::TempDir;
+    use wiremock::Mock;
+    use wiremock::MockServer;
+    use wiremock::ResponseTemplate;
+    use wiremock::matchers::method;
+    use wiremock::matchers::path;
+
+    const SSE_TOOL_CALL_ADD: &str = r#"[
+  {
+    "type": "response.output_item.done",
+    "item": {
+      "type": "function_call",
+      "name": "apply_patch",
+      "arguments": "{\n  \"input\": \"*** Begin Patch\\n*** Add File: test.md\\n+Hello world\\n*** End Patch\"\n}",
+      "call_id": "__ID__"
+    }
+  },
+  {
+    "type": "response.completed",
+    "response": {
+      "id": "__ID__",
+      "usage": {
+        "input_tokens": 0,
+        "input_tokens_details": null,
+        "output_tokens": 0,
+        "output_tokens_details": null,
+        "total_tokens": 0
+      },
+      "output": []
+    }
+  }
+]"#;
+
+    const SSE_TOOL_CALL_UPDATE: &str = r#"[
+  {
+    "type": "response.output_item.done",
+    "item": {
+      "type": "function_call",
+      "name": "apply_patch",
+      "arguments": "{\n  \"input\": \"*** Begin Patch\\n*** Update File: test.md\\n@@\\n-Hello world\\n+Final text\\n*** End Patch\"\n}",
+      "call_id": "__ID__"
+    }
+  },
+  {
+    "type": "response.completed",
+    "response": {
+      "id": "__ID__",
+      "usage": {
+        "input_tokens": 0,
+        "input_tokens_details": null,
+        "output_tokens": 0,
+        "output_tokens_details": null,
+        "total_tokens": 0
+      },
+      "output": []
+    }
+  }
+]"#;
+
+    const SSE_TOOL_CALL_COMPLETED: &str = r#"[
+  {
+    "type": "response.completed",
+    "response": {
+      "id": "__ID__",
+      "usage": {
+        "input_tokens": 0,
+        "input_tokens_details": null,
+        "output_tokens": 0,
+        "output_tokens_details": null,
+        "total_tokens": 0
+      },
+      "output": []
+    }
+  }
+]"#;
+
+    // Start a mock model server
+    let server = MockServer::start().await;
+
+    // First response: model calls apply_patch to create test.md
+    let first = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(
+            load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_ADD, "call1"),
+            "text/event-stream",
+        );
+
+    Mock::given(method("POST"))
+        // .and(path("/v1/responses"))
+        .respond_with(first)
+        .up_to_n_times(1)
+        .mount(&server)
+        .await;
+
+    // Second response: model calls apply_patch to update test.md
+    let second = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(
+            load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_UPDATE, "call2"),
+            "text/event-stream",
+        );
+
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(second)
+        .up_to_n_times(1)
+        .mount(&server)
+        .await;
+
+    let final_completed = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(
+            load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_COMPLETED, "resp3"),
+            "text/event-stream",
+        );
+
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(final_completed)
+        .expect(1)
+        .mount(&server)
+        .await;
+
+    let tmp_cwd = TempDir::new().unwrap();
+    Command::cargo_bin("codex-exec")
+        .context("should find binary for codex-exec")?
+        .current_dir(tmp_cwd.path())
+        .env("CODEX_HOME", tmp_cwd.path())
+        .env("OPENAI_API_KEY", "dummy")
+        .env("OPENAI_BASE_URL", format!("{}/v1", server.uri()))
+        .arg("--skip-git-repo-check")
+        .arg("-s")
+        .arg("workspace-write")
+        .arg("foo")
+        .assert()
+        .success();
+
+    // Verify final file contents
+    let final_path = tmp_cwd.path().join("test.md");
+    let contents = std::fs::read_to_string(&final_path)
+        .unwrap_or_else(|e| panic!("failed reading {}: {e}", final_path.display()));
+    assert_eq!(contents, "Final text\n");
+    Ok(())
+}
+
+#[cfg(not(target_os = "windows"))]
+#[tokio::test]
+async fn test_apply_patch_freeform_tool() -> anyhow::Result<()> {
+    use core_test_support::load_sse_fixture_with_id_from_str;
+    use tempfile::TempDir;
+    use wiremock::Mock;
+    use wiremock::MockServer;
+    use wiremock::ResponseTemplate;
+    use wiremock::matchers::method;
+    use wiremock::matchers::path;
+
+    const SSE_TOOL_CALL_ADD: &str = r#"[
+  {
+    "type": "response.output_item.done",
+    "item": {
+      "type": "custom_tool_call",
+      "name": "apply_patch",
+      "input": "*** Begin Patch\n*** Add File: test.md\n+Hello world\n*** End Patch",
+      "call_id": "__ID__"
+    }
+  },
+  {
+    "type": "response.completed",
+    "response": {
+      "id": "__ID__",
+      "usage": {
+        "input_tokens": 0,
+        "input_tokens_details": null,
+        "output_tokens": 0,
+        "output_tokens_details": null,
+        "total_tokens": 0
+      },
+      "output": []
+    }
+  }
+]"#;
+
+    const SSE_TOOL_CALL_UPDATE: &str = r#"[
+  {
+    "type": "response.output_item.done",
+    "item": {
+      "type": "custom_tool_call",
+      "name": "apply_patch",
+      "input": "*** Begin Patch\n*** Update File: test.md\n@@\n-Hello world\n+Final text\n*** End Patch",
+      "call_id": "__ID__"
+    }
+  },
+  {
+    "type": "response.completed",
+    "response": {
+      "id": "__ID__",
+      "usage": {
+        "input_tokens": 0,
+        "input_tokens_details": null,
+        "output_tokens": 0,
+        "output_tokens_details": null,
+        "total_tokens": 0
+      },
+      "output": []
+    }
+  }
+]"#;
+
+    const SSE_TOOL_CALL_COMPLETED: &str = r#"[
+  {
+    "type": "response.completed",
+    "response": {
+      "id": "__ID__",
+      "usage": {
+        "input_tokens": 0,
+        "input_tokens_details": null,
+        "output_tokens": 0,
+        "output_tokens_details": null,
+        "total_tokens": 0
+      },
+      "output": []
+    }
+  }
+]"#;
+
+    // Start a mock model server
+    let server = MockServer::start().await;
+
+    // First response: model calls apply_patch to create test.md
+    let first = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(
+            load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_ADD, "call1"),
+            "text/event-stream",
+        );
+
+    Mock::given(method("POST"))
+        // .and(path("/v1/responses"))
+        .respond_with(first)
+        .up_to_n_times(1)
+        .mount(&server)
+        .await;
+
+    // Second response: model calls apply_patch to update test.md
+    let second = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(
+            load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_UPDATE, "call2"),
+            "text/event-stream",
+        );
+
+    Mock::given(method("POST"))
+        .and(path("/v1/responses"))
+        .respond_with(second)
+        .up_to_n_times(1)
+        .mount(&server)
+        .await;
+
+    let final_completed = ResponseTemplate::new(200)
+        .insert_header("content-type", "text/event-stream")
+        .set_body_raw(
+            load_sse_fixture_with_id_from_str(SSE_TOOL_CALL_COMPLETED, "resp3"),
+            "text/event-stream",
+        );
+
+    Mock::given(method("POST"))
+        // .and(path("/v1/responses"))
+        .respond_with(final_completed)
+        .expect(1)
+        .mount(&server)
+        .await;
+
+    let tmp_cwd = TempDir::new().unwrap();
+    Command::cargo_bin("codex-exec")
+        .context("should find binary for codex-exec")?
+        .current_dir(tmp_cwd.path())
+        .env("CODEX_HOME", tmp_cwd.path())
+        .env("OPENAI_API_KEY", "dummy")
+        .env("OPENAI_BASE_URL", format!("{}/v1", server.uri()))
+        .arg("--skip-git-repo-check")
+        .arg("-s")
+        .arg("workspace-write")
+        .arg("foo")
+        .assert()
+        .success();
+
+    // Verify final file contents
+    let final_path = tmp_cwd.path().join("test.md");
+    let contents = std::fs::read_to_string(&final_path)
+        .unwrap_or_else(|e| panic!("failed reading {}: {e}", final_path.display()));
+    assert_eq!(contents, "Final text\n");
+    Ok(())
+}

codex-rs/execpolicy/Cargo.toml

@@ -26,7 +26,7 @@ multimap = "0.10.0"
 path-absolutize = "3.1.1"
 regex-lite = "0.1"
 serde = { version = "1.0.194", features = ["derive"] }
-serde_json = "1.0.142"
+serde_json = "1.0.143"
 serde_with = { version = "3", features = ["macros"] }
 
 [dev-dependencies]

codex-rs/execpolicy/src/execv_checker.rs

@@ -214,7 +214,12 @@ system_path=[{fake_cp:?}]
 
         // Only readable folders specified.
         assert_eq!(
-            checker.check(valid_exec.clone(), &cwd, &[root_path.clone()], &[]),
+            checker.check(
+                valid_exec.clone(),
+                &cwd,
+                std::slice::from_ref(&root_path),
+                &[]
+            ),
             Err(WriteablePathNotInWriteableFolders {
                 file: dest_path.clone(),
                 folders: vec![]
@@ -226,8 +231,8 @@ system_path=[{fake_cp:?}]
             checker.check(
                 valid_exec.clone(),
                 &cwd,
-                &[root_path.clone()],
-                &[root_path.clone()]
+                std::slice::from_ref(&root_path),
+                std::slice::from_ref(&root_path)
             ),
             Ok(cp.clone()),
         );
@@ -246,8 +251,8 @@ system_path=[{fake_cp:?}]
             checker.check(
                 valid_exec_call_folders_as_args,
                 &cwd,
-                &[root_path.clone()],
-                &[root_path.clone()]
+                std::slice::from_ref(&root_path),
+                std::slice::from_ref(&root_path)
             ),
             Ok(cp.clone()),
         );
@@ -269,8 +274,8 @@ system_path=[{fake_cp:?}]
             checker.check(
                 exec_with_parent_of_readable_folder,
                 &cwd,
-                &[root_path.clone()],
-                &[dest_path.clone()]
+                std::slice::from_ref(&root_path),
+                std::slice::from_ref(&dest_path)
             ),
             Err(ReadablePathNotInReadableFolders {
                 file: root_path.parent().unwrap().to_path_buf(),

codex-rs/execpolicy/src/policy.rs

@@ -56,16 +56,16 @@ impl Policy {
         }
 
         for arg in args {
-            if let Some(regex) = &self.forbidden_substrings_pattern {
-                if regex.is_match(arg) {
-                    return Ok(MatchedExec::Forbidden {
-                        cause: Forbidden::Arg {
-                            arg: arg.clone(),
-                            exec_call: exec_call.clone(),
-                        },
-                        reason: format!("arg `{arg}` contains forbidden substring"),
-                    });
-                }
+            if let Some(regex) = &self.forbidden_substrings_pattern
+                && regex.is_match(arg)
+            {
+                return Ok(MatchedExec::Forbidden {
+                    cause: Forbidden::Arg {
+                        arg: arg.clone(),
+                        exec_call: exec_call.clone(),
+                    },
+                    reason: format!("arg `{arg}` contains forbidden substring"),
+                });
             }
         }
 

codex-rs/execpolicy/src/sed_command.rs

@@ -3,12 +3,12 @@ use crate::error::Result;
 
 pub fn parse_sed_command(sed_command: &str) -> Result<()> {
     // For now, we parse only commands like `122,202p`.
-    if let Some(stripped) = sed_command.strip_suffix("p") {
-        if let Some((first, rest)) = stripped.split_once(",") {
-            if first.parse::<u64>().is_ok() && rest.parse::<u64>().is_ok() {
-                return Ok(());
-            }
-        }
+    if let Some(stripped) = sed_command.strip_suffix("p")
+        && let Some((first, rest)) = stripped.split_once(",")
+        && first.parse::<u64>().is_ok()
+        && rest.parse::<u64>().is_ok()
+    {
+        return Ok(());
     }
 
     Err(Error::SedCommandNotProvablySafe {

codex-rs/file-search/Cargo.toml

@@ -17,5 +17,5 @@ clap = { version = "4", features = ["derive"] }
 ignore = "0.4.23"
 nucleo-matcher = "0.3.1"
 serde = { version = "1", features = ["derive"] }
-serde_json = "1.0.142"
+serde_json = "1.0.143"
 tokio = { version = "1", features = ["full"] }

codex-rs/file-search/src/lib.rs

@@ -228,11 +228,11 @@ pub fn run(
         for &Reverse((score, ref line)) in best_list.binary_heap.iter() {
             if global_heap.len() < limit.get() {
                 global_heap.push(Reverse((score, line.clone())));
-            } else if let Some(min_element) = global_heap.peek() {
-                if score > min_element.0.0 {
-                    global_heap.pop();
-                    global_heap.push(Reverse((score, line.clone())));
-                }
+            } else if let Some(min_element) = global_heap.peek()
+                && score > min_element.0.0
+            {
+                global_heap.pop();
+                global_heap.push(Reverse((score, line.clone())));
             }
         }
     }
@@ -320,11 +320,11 @@ impl BestMatchesList {
 
             if self.binary_heap.len() < self.max_count {
                 self.binary_heap.push(Reverse((score, line.to_string())));
-            } else if let Some(min_element) = self.binary_heap.peek() {
-                if score > min_element.0.0 {
-                    self.binary_heap.pop();
-                    self.binary_heap.push(Reverse((score, line.to_string())));
-                }
+            } else if let Some(min_element) = self.binary_heap.peek()
+                && score > min_element.0.0
+            {
+                self.binary_heap.pop();
+                self.binary_heap.push(Reverse((score, line.to_string())));
             }
         }
     }

codex-rs/justfile

@@ -24,8 +24,8 @@ file-search *args:
 fmt:
     cargo fmt -- --config imports_granularity=Item
 
-fix:
-    cargo clippy --fix --all-features --tests --allow-dirty
+fix *args:
+    cargo clippy --fix --all-features --tests --allow-dirty "$@"
 
 install:
     rustup show active-toolchain

codex-rs/linux-sandbox/Cargo.toml

@@ -20,7 +20,7 @@ clap = { version = "4", features = ["derive"] }
 codex-common = { path = "../common", features = ["cli"] }
 codex-core = { path = "../core" }
 landlock = "0.4.1"
-libc = "0.2.172"
+libc = "0.2.175"
 seccompiler = "0.5.0"
 
 [target.'cfg(target_os = "linux")'.dev-dependencies]

codex-rs/login/Cargo.toml

@@ -9,6 +9,7 @@ workspace = true
 [dependencies]
 base64 = "0.22"
 chrono = { version = "0.4", features = ["serde"] }
+codex-protocol = { path = "../protocol" }
 rand = "0.8"
 reqwest = { version = "0.12", features = ["json", "blocking"] }
 serde = { version = "1", features = ["derive"] }

codex-rs/login/src/auth_manager.rs

@@ -0,0 +1,129 @@
+use std::path::PathBuf;
+use std::sync::Arc;
+use std::sync::RwLock;
+
+use crate::AuthMode;
+use crate::CodexAuth;
+
+/// Internal cached auth state.
+#[derive(Clone, Debug)]
+struct CachedAuth {
+    preferred_auth_mode: AuthMode,
+    auth: Option<CodexAuth>,
+}
+
+/// Central manager providing a single source of truth for auth.json derived
+/// authentication data. It loads once (or on preference change) and then
+/// hands out cloned `CodexAuth` values so the rest of the program has a
+/// consistent snapshot.
+///
+/// External modifications to `auth.json` will NOT be observed until
+/// `reload()` is called explicitly. This matches the design goal of avoiding
+/// different parts of the program seeing inconsistent auth data mid‑run.
+#[derive(Debug)]
+pub struct AuthManager {
+    codex_home: PathBuf,
+    inner: RwLock<CachedAuth>,
+}
+
+impl AuthManager {
+    /// Create a new manager loading the initial auth using the provided
+    /// preferred auth method. Errors loading auth are swallowed; `auth()` will
+    /// simply return `None` in that case so callers can treat it as an
+    /// unauthenticated state.
+    pub fn new(codex_home: PathBuf, preferred_auth_mode: AuthMode) -> Self {
+        let auth = crate::CodexAuth::from_codex_home(&codex_home, preferred_auth_mode)
+            .ok()
+            .flatten();
+        Self {
+            codex_home,
+            inner: RwLock::new(CachedAuth {
+                preferred_auth_mode,
+                auth,
+            }),
+        }
+    }
+
+    /// Create an AuthManager with a specific CodexAuth, for testing only.
+    pub fn from_auth_for_testing(auth: CodexAuth) -> Arc<Self> {
+        let preferred_auth_mode = auth.mode;
+        let cached = CachedAuth {
+            preferred_auth_mode,
+            auth: Some(auth),
+        };
+        Arc::new(Self {
+            codex_home: PathBuf::new(),
+            inner: RwLock::new(cached),
+        })
+    }
+
+    /// Current cached auth (clone). May be `None` if not logged in or load failed.
+    pub fn auth(&self) -> Option<CodexAuth> {
+        self.inner.read().ok().and_then(|c| c.auth.clone())
+    }
+
+    /// Preferred auth method used when (re)loading.
+    pub fn preferred_auth_method(&self) -> AuthMode {
+        self.inner
+            .read()
+            .map(|c| c.preferred_auth_mode)
+            .unwrap_or(AuthMode::ApiKey)
+    }
+
+    /// Force a reload using the existing preferred auth method. Returns
+    /// whether the auth value changed.
+    pub fn reload(&self) -> bool {
+        let preferred = self.preferred_auth_method();
+        let new_auth = crate::CodexAuth::from_codex_home(&self.codex_home, preferred)
+            .ok()
+            .flatten();
+        if let Ok(mut guard) = self.inner.write() {
+            let changed = !AuthManager::auths_equal(&guard.auth, &new_auth);
+            guard.auth = new_auth;
+            changed
+        } else {
+            false
+        }
+    }
+
+    fn auths_equal(a: &Option<CodexAuth>, b: &Option<CodexAuth>) -> bool {
+        match (a, b) {
+            (None, None) => true,
+            (Some(a), Some(b)) => a == b,
+            _ => false,
+        }
+    }
+
+    /// Convenience constructor returning an `Arc` wrapper.
+    pub fn shared(codex_home: PathBuf, preferred_auth_mode: AuthMode) -> Arc<Self> {
+        Arc::new(Self::new(codex_home, preferred_auth_mode))
+    }
+
+    /// Attempt to refresh the current auth token (if any). On success, reload
+    /// the auth state from disk so other components observe refreshed token.
+    pub async fn refresh_token(&self) -> std::io::Result<Option<String>> {
+        let auth = match self.auth() {
+            Some(a) => a,
+            None => return Ok(None),
+        };
+        match auth.refresh_token().await {
+            Ok(token) => {
+                // Reload to pick up persisted changes.
+                self.reload();
+                Ok(Some(token))
+            }
+            Err(e) => Err(e),
+        }
+    }
+
+    /// Log out by deleting the on‑disk auth.json (if present). Returns Ok(true)
+    /// if a file was removed, Ok(false) if no auth file existed. On success,
+    /// reloads the in‑memory auth cache so callers immediately observe the
+    /// unauthenticated state.
+    pub fn logout(&self) -> std::io::Result<bool> {
+        let removed = crate::logout(&self.codex_home)?;
+        // Always reload to clear any cached auth (even if file absent).
+        self.reload();
+        Ok(removed)
+    }
+}

codex-rs/login/src/lib.rs

@@ -16,25 +16,22 @@ use std::sync::Arc;
 use std::sync::Mutex;
 use std::time::Duration;
 
-pub use crate::server::LoginServerInfo;
+pub use crate::server::LoginServer;
 pub use crate::server::ServerOptions;
-pub use crate::server::run_server_blocking;
-pub use crate::server::run_server_blocking_with_notify;
+pub use crate::server::ShutdownHandle;
+pub use crate::server::run_login_server;
 pub use crate::token_data::TokenData;
 use crate::token_data::parse_id_token;
 
+mod auth_manager;
 mod pkce;
 mod server;
 mod token_data;
 
 pub const CLIENT_ID: &str = "app_EMoamEEZ73f0CkXaXp7hrann";
 pub const OPENAI_API_KEY_ENV_VAR: &str = "OPENAI_API_KEY";
-
-#[derive(Clone, Debug, PartialEq, Copy)]
-pub enum AuthMode {
-    ApiKey,
-    ChatGPT,
-}
+pub use auth_manager::AuthManager;
+pub use codex_protocol::mcp_protocol::AuthMode;
 
 #[derive(Debug, Clone)]
 pub struct CodexAuth {
@@ -61,10 +58,46 @@ impl CodexAuth {
         }
     }
 
+    pub async fn refresh_token(&self) -> Result<String, std::io::Error> {
+        let token_data = self
+            .get_current_token_data()
+            .ok_or(std::io::Error::other("Token data is not available."))?;
+        let token = token_data.refresh_token;
+
+        let refresh_response = try_refresh_token(token)
+            .await
+            .map_err(std::io::Error::other)?;
+
+        let updated = update_tokens(
+            &self.auth_file,
+            refresh_response.id_token,
+            refresh_response.access_token,
+            refresh_response.refresh_token,
+        )
+        .await?;
+
+        if let Ok(mut auth_lock) = self.auth_dot_json.lock() {
+            *auth_lock = Some(updated.clone());
+        }
+
+        let access = match updated.tokens {
+            Some(t) => t.access_token,
+            None => {
+                return Err(std::io::Error::other(
+                    "Token data is not available after refresh.",
+                ));
+            }
+        };
+        Ok(access)
+    }
+
     /// Loads the available auth information from the auth.json or
     /// OPENAI_API_KEY environment variable.
-    pub fn from_codex_home(codex_home: &Path) -> std::io::Result<Option<CodexAuth>> {
-        load_auth(codex_home, true)
+    pub fn from_codex_home(
+        codex_home: &Path,
+        preferred_auth_method: AuthMode,
+    ) -> std::io::Result<Option<CodexAuth>> {
+        load_auth(codex_home, true, preferred_auth_method)
     }
 
     pub async fn get_token_data(&self) -> Result<TokenData, std::io::Error> {
@@ -165,7 +198,11 @@ impl CodexAuth {
     }
 }
 
-fn load_auth(codex_home: &Path, include_env_var: bool) -> std::io::Result<Option<CodexAuth>> {
+fn load_auth(
+    codex_home: &Path,
+    include_env_var: bool,
+    preferred_auth_method: AuthMode,
+) -> std::io::Result<Option<CodexAuth>> {
     // First, check to see if there is a valid auth.json file. If not, we fall
     // back to AuthMode::ApiKey using the OPENAI_API_KEY environment variable
     // (if it is set).
@@ -201,7 +238,7 @@ fn load_auth(codex_home: &Path, include_env_var: bool) -> std::io::Result<Option
         // "refreshable" even if we are using the API key for auth?
         match &tokens {
             Some(tokens) => {
-                if tokens.is_plan_that_should_use_api_key() {
+                if tokens.should_use_api_key(preferred_auth_method, tokens.is_openai_email()) {
                     return Ok(Some(CodexAuth::from_api_key(api_key)));
                 } else {
                     // Ignore the API key and fall through to ChatGPT auth.
@@ -252,65 +289,6 @@ pub fn logout(codex_home: &Path) -> std::io::Result<bool> {
     }
 }
 
-/// Represents a running login server. The server can be stopped by calling `cancel()` on SpawnedLogin.
-#[derive(Debug, Clone)]
-pub struct SpawnedLogin {
-    url: Arc<Mutex<Option<String>>>,
-    done: Arc<Mutex<Option<bool>>>,
-    shutdown: Arc<std::sync::atomic::AtomicBool>,
-}
-
-impl SpawnedLogin {
-    pub fn get_login_url(&self) -> Option<String> {
-        self.url.lock().ok().and_then(|u| u.clone())
-    }
-
-    pub fn get_auth_result(&self) -> Option<bool> {
-        self.done.lock().ok().and_then(|d| *d)
-    }
-
-    pub fn cancel(&self) {
-        self.shutdown
-            .store(true, std::sync::atomic::Ordering::SeqCst);
-    }
-}
-
-pub fn spawn_login_with_chatgpt(codex_home: &Path) -> std::io::Result<SpawnedLogin> {
-    let (tx, rx) = std::sync::mpsc::channel::<LoginServerInfo>();
-    let shutdown = Arc::new(std::sync::atomic::AtomicBool::new(false));
-    let done = Arc::new(Mutex::new(None::<bool>));
-    let url = Arc::new(Mutex::new(None::<String>));
-
-    let codex_home_buf = codex_home.to_path_buf();
-    let client_id = CLIENT_ID.to_string();
-
-    let shutdown_clone = shutdown.clone();
-    let done_clone = done.clone();
-    std::thread::spawn(move || {
-        let opts = ServerOptions::new(&codex_home_buf, &client_id);
-        let res = run_server_blocking_with_notify(opts, Some(tx), Some(shutdown_clone));
-        let success = res.is_ok();
-        if let Ok(mut lock) = done_clone.lock() {
-            *lock = Some(success);
-        }
-    });
-
-    let url_clone = url.clone();
-    std::thread::spawn(move || {
-        if let Ok(u) = rx.recv() {
-            if let Ok(mut lock) = url_clone.lock() {
-                *lock = Some(u.auth_url);
-            }
-        }
-    });
-
-    Ok(SpawnedLogin {
-        url,
-        done,
-        shutdown,
-    })
-}
-
 pub fn login_with_api_key(codex_home: &Path, api_key: &str) -> std::io::Result<()> {
     let auth_dot_json = AuthDotJson {
         openai_api_key: Some(api_key.to_string()),
@@ -442,7 +420,9 @@ mod tests {
     fn writes_api_key_and_loads_auth() {
         let dir = tempdir().unwrap();
         login_with_api_key(dir.path(), "sk-test-key").unwrap();
-        let auth = load_auth(dir.path(), false).unwrap().unwrap();
+        let auth = load_auth(dir.path(), false, AuthMode::ChatGPT)
+            .unwrap()
+            .unwrap();
         assert_eq!(auth.mode, AuthMode::ApiKey);
         assert_eq!(auth.api_key.as_deref(), Some("sk-test-key"));
     }
@@ -454,7 +434,9 @@ mod tests {
         let env_var = std::env::var(OPENAI_API_KEY_ENV_VAR);
 
         if let Ok(env_var) = env_var {
-            let auth = load_auth(dir.path(), true).unwrap().unwrap();
+            let auth = load_auth(dir.path(), true, AuthMode::ChatGPT)
+                .unwrap()
+                .unwrap();
             assert_eq!(auth.mode, AuthMode::ApiKey);
             assert_eq!(auth.api_key, Some(env_var));
         }
@@ -497,7 +479,9 @@ mod tests {
             mode,
             auth_dot_json,
             auth_file: _,
-        } = load_auth(codex_home.path(), false).unwrap().unwrap();
+        } = load_auth(codex_home.path(), false, AuthMode::ChatGPT)
+            .unwrap()
+            .unwrap();
         assert_eq!(None, api_key);
         assert_eq!(AuthMode::ChatGPT, mode);
 
@@ -546,7 +530,9 @@ mod tests {
             mode,
             auth_dot_json,
             auth_file: _,
-        } = load_auth(codex_home.path(), false).unwrap().unwrap();
+        } = load_auth(codex_home.path(), false, AuthMode::ChatGPT)
+            .unwrap()
+            .unwrap();
         assert_eq!(None, api_key);
         assert_eq!(AuthMode::ChatGPT, mode);
 
@@ -594,7 +580,9 @@ mod tests {
             mode,
             auth_dot_json,
             auth_file: _,
-        } = load_auth(codex_home.path(), false).unwrap().unwrap();
+        } = load_auth(codex_home.path(), false, AuthMode::ChatGPT)
+            .unwrap()
+            .unwrap();
         assert_eq!(Some("sk-test-key".to_string()), api_key);
         assert_eq!(AuthMode::ApiKey, mode);
 
@@ -683,7 +671,9 @@ mod tests {
         )
         .unwrap();
 
-        let auth = load_auth(dir.path(), false).unwrap().unwrap();
+        let auth = load_auth(dir.path(), false, AuthMode::ChatGPT)
+            .unwrap()
+            .unwrap();
         assert_eq!(auth.mode, AuthMode::ApiKey);
         assert_eq!(auth.api_key, Some("sk-test-key".to_string()));
 

codex-rs/login/src/server.rs

@@ -1,39 +1,41 @@
+use std::io::Cursor;
 use std::io::{self};
 use std::path::Path;
+use std::path::PathBuf;
 use std::sync::Arc;
-use std::sync::atomic::AtomicBool;
-use std::sync::atomic::Ordering;
-
-use base64::Engine;
-use chrono::Utc;
-use rand::RngCore;
-use tiny_http::Response;
-use tiny_http::Server;
+use std::thread;
 
 use crate::AuthDotJson;
 use crate::get_auth_file;
 use crate::pkce::PkceCodes;
 use crate::pkce::generate_pkce;
+use base64::Engine;
+use chrono::Utc;
+use rand::RngCore;
+use tiny_http::Header;
+use tiny_http::Request;
+use tiny_http::Response;
+use tiny_http::Server;
 
 const DEFAULT_ISSUER: &str = "https://auth.openai.com";
 const DEFAULT_PORT: u16 = 1455;
 
 #[derive(Debug, Clone)]
-pub struct ServerOptions<'a> {
-    pub codex_home: &'a Path,
-    pub client_id: &'a str,
-    pub issuer: &'a str,
+pub struct ServerOptions {
+    pub codex_home: PathBuf,
+    pub client_id: String,
+    pub issuer: String,
     pub port: u16,
     pub open_browser: bool,
     pub force_state: Option<String>,
 }
 
-impl<'a> ServerOptions<'a> {
-    pub fn new(codex_home: &'a Path, client_id: &'a str) -> Self {
+impl ServerOptions {
+    pub fn new(codex_home: PathBuf, client_id: String) -> Self {
         Self {
             codex_home,
-            client_id,
-            issuer: DEFAULT_ISSUER,
+            client_id: client_id.to_string(),
+            issuer: DEFAULT_ISSUER.to_string(),
             port: DEFAULT_PORT,
             open_browser: true,
             force_state: None,
@@ -41,21 +43,41 @@ impl<'a> ServerOptions<'a> {
     }
 }
 
-#[allow(dead_code)]
-pub fn run_server_blocking(opts: ServerOptions) -> io::Result<()> {
-    run_server_blocking_with_notify(opts, None, None)
-}
-
-pub struct LoginServerInfo {
+pub struct LoginServer {
     pub auth_url: String,
     pub actual_port: u16,
+    server_handle: tokio::task::JoinHandle<io::Result<()>>,
+    shutdown_handle: ShutdownHandle,
 }
 
-pub fn run_server_blocking_with_notify(
-    opts: ServerOptions,
-    notify_started: Option<std::sync::mpsc::Sender<LoginServerInfo>>,
-    shutdown_flag: Option<Arc<AtomicBool>>,
-) -> io::Result<()> {
+impl LoginServer {
+    pub async fn block_until_done(self) -> io::Result<()> {
+        self.server_handle
+            .await
+            .map_err(|err| io::Error::other(format!("login server thread panicked: {err:?}")))?
+    }
+
+    pub fn cancel(&self) {
+        self.shutdown_handle.shutdown();
+    }
+
+    pub fn cancel_handle(&self) -> ShutdownHandle {
+        self.shutdown_handle.clone()
+    }
+}
+
+#[derive(Clone, Debug)]
+pub struct ShutdownHandle {
+    shutdown_notify: Arc<tokio::sync::Notify>,
+}
+
+impl ShutdownHandle {
+    pub fn shutdown(&self) {
+        self.shutdown_notify.notify_waiters();
+    }
+}
+
+pub fn run_login_server(opts: ServerOptions) -> io::Result<LoginServer> {
     let pkce = generate_pkce();
     let state = opts.force_state.clone().unwrap_or_else(generate_state);
 
@@ -69,137 +91,184 @@ pub fn run_server_blocking_with_notify(
             ));
         }
     };
+    let server = Arc::new(server);
 
     let redirect_uri = format!("http://localhost:{actual_port}/auth/callback");
-    let auth_url = build_authorize_url(opts.issuer, opts.client_id, &redirect_uri, &pkce, &state);
-
-    if let Some(tx) = &notify_started {
-        let _ = tx.send(LoginServerInfo {
-            auth_url: auth_url.clone(),
-            actual_port,
-        });
-    }
+    let auth_url = build_authorize_url(&opts.issuer, &opts.client_id, &redirect_uri, &pkce, &state);
 
     if opts.open_browser {
         let _ = webbrowser::open(&auth_url);
     }
 
-    let shutdown_flag = shutdown_flag.unwrap_or_else(|| Arc::new(AtomicBool::new(false)));
-    while !shutdown_flag.load(Ordering::SeqCst) {
-        let req = match server.recv() {
-            Ok(r) => r,
-            Err(e) => return Err(io::Error::other(e)),
-        };
-
-        let url_raw = req.url().to_string();
-        let parsed_url = match url::Url::parse(&format!("http://localhost{url_raw}")) {
-            Ok(u) => u,
-            Err(e) => {
-                eprintln!("URL parse error: {e}");
-                let _ = req.respond(Response::from_string("Bad Request").with_status_code(400));
-                continue;
+    // Map blocking reads from server.recv() to an async channel.
+    let (tx, mut rx) = tokio::sync::mpsc::channel::<Request>(16);
+    let _server_handle = {
+        let server = server.clone();
+        thread::spawn(move || -> io::Result<()> {
+            while let Ok(request) = server.recv() {
+                tx.blocking_send(request).map_err(|e| {
+                    eprintln!("Failed to send request to channel: {e}");
+                    io::Error::other("Failed to send request to channel")
+                })?;
             }
-        };
-        let path = parsed_url.path().to_string();
+            Ok(())
+        })
+    };
 
-        match path.as_str() {
-            "/auth/callback" => {
-                let params: std::collections::HashMap<String, String> =
-                    parsed_url.query_pairs().into_owned().collect();
-                if params.get("state").map(String::as_str) != Some(state.as_str()) {
-                    let _ =
-                        req.respond(Response::from_string("State mismatch").with_status_code(400));
-                    continue;
+    let shutdown_notify = Arc::new(tokio::sync::Notify::new());
+    let server_handle = {
+        let shutdown_notify = shutdown_notify.clone();
+        let server = server.clone();
+        tokio::spawn(async move {
+            let result = loop {
+                tokio::select! {
+                    _ = shutdown_notify.notified() => {
+                        break Err(io::Error::other("Login was not completed"));
+                    }
+                    maybe_req = rx.recv() => {
+                        let Some(req) = maybe_req else {
+                            break Err(io::Error::other("Login was not completed"));
+                        };
+
+                        let url_raw = req.url().to_string();
+                        let response =
+                            process_request(&url_raw, &opts, &redirect_uri, &pkce, actual_port, &state).await;
+
+                        let is_login_complete = matches!(response, HandledRequest::ResponseAndExit(_));
+                        match response {
+                            HandledRequest::Response(r) | HandledRequest::ResponseAndExit(r) => {
+                                let _ = tokio::task::spawn_blocking(move || req.respond(r)).await;
+                            }
+                            HandledRequest::RedirectWithHeader(header) => {
+                                let redirect = Response::empty(302).with_header(header);
+                                let _ = tokio::task::spawn_blocking(move || req.respond(redirect)).await;
+                            }
+                        }
+
+                        if is_login_complete {
+                            break Ok(());
+                        }
+                    }
                 }
-                let code = match params.get("code") {
-                    Some(c) if !c.is_empty() => c.clone(),
-                    _ => {
-                        let _ = req.respond(
-                            Response::from_string("Missing authorization code")
-                                .with_status_code(400),
-                        );
-                        continue;
-                    }
-                };
+            };
 
-                match exchange_code_for_tokens(
-                    opts.issuer,
-                    opts.client_id,
-                    &redirect_uri,
-                    &pkce,
-                    &code,
-                ) {
-                    Ok(tokens) => {
-                        // Obtain API key via token-exchange and persist
-                        let api_key =
-                            obtain_api_key(opts.issuer, opts.client_id, &tokens.id_token).ok();
-                        if let Err(err) = persist_tokens(
-                            opts.codex_home,
-                            api_key.clone(),
-                            tokens.id_token.clone(),
-                            Some(tokens.access_token.clone()),
-                            Some(tokens.refresh_token.clone()),
-                        ) {
-                            eprintln!("Persist error: {err}");
-                            let _ = req.respond(
-                                Response::from_string(format!(
-                                    "Unable to persist auth file: {err}"
-                                ))
-                                .with_status_code(500),
-                            );
-                            continue;
-                        }
+            // Ensure that the server is unblocked so the thread dedicated to
+            // running `server.recv()` in a loop exits cleanly.
+            server.unblock();
+            result
+        })
+    };
 
-                        let success_url = compose_success_url(
-                            actual_port,
-                            opts.issuer,
-                            &tokens.id_token,
-                            &tokens.access_token,
-                        );
-                        match tiny_http::Header::from_bytes(
-                            &b"Location"[..],
-                            success_url.as_bytes(),
-                        ) {
-                            Ok(h) => {
-                                let response = tiny_http::Response::empty(302).with_header(h);
-                                let _ = req.respond(response);
-                            }
-                            Err(_) => {
-                                let _ = req.respond(
-                                    Response::from_string("Internal Server Error")
-                                        .with_status_code(500),
-                                );
-                            }
-                        }
-                    }
-                    Err(err) => {
-                        eprintln!("Token exchange error: {err}");
-                        let _ = req.respond(
-                            Response::from_string(format!("Token exchange failed: {err}"))
+    Ok(LoginServer {
+        auth_url,
+        actual_port,
+        server_handle,
+        shutdown_handle: ShutdownHandle { shutdown_notify },
+    })
+}
+
+enum HandledRequest {
+    Response(Response<Cursor<Vec<u8>>>),
+    RedirectWithHeader(Header),
+    ResponseAndExit(Response<Cursor<Vec<u8>>>),
+}
+
+async fn process_request(
+    url_raw: &str,
+    opts: &ServerOptions,
+    redirect_uri: &str,
+    pkce: &PkceCodes,
+    actual_port: u16,
+    state: &str,
+) -> HandledRequest {
+    let parsed_url = match url::Url::parse(&format!("http://localhost{url_raw}")) {
+        Ok(u) => u,
+        Err(e) => {
+            eprintln!("URL parse error: {e}");
+            return HandledRequest::Response(
+                Response::from_string("Bad Request").with_status_code(400),
+            );
+        }
+    };
+    let path = parsed_url.path().to_string();
+
+    match path.as_str() {
+        "/auth/callback" => {
+            let params: std::collections::HashMap<String, String> =
+                parsed_url.query_pairs().into_owned().collect();
+            if params.get("state").map(String::as_str) != Some(state) {
+                return HandledRequest::Response(
+                    Response::from_string("State mismatch").with_status_code(400),
+                );
+            }
+            let code = match params.get("code") {
+                Some(c) if !c.is_empty() => c.clone(),
+                _ => {
+                    return HandledRequest::Response(
+                        Response::from_string("Missing authorization code").with_status_code(400),
+                    );
+                }
+            };
+
+            match exchange_code_for_tokens(&opts.issuer, &opts.client_id, redirect_uri, pkce, &code)
+                .await
+            {
+                Ok(tokens) => {
+                    // Obtain API key via token-exchange and persist
+                    let api_key = obtain_api_key(&opts.issuer, &opts.client_id, &tokens.id_token)
+                        .await
+                        .ok();
+                    if let Err(err) = persist_tokens_async(
+                        &opts.codex_home,
+                        api_key.clone(),
+                        tokens.id_token.clone(),
+                        Some(tokens.access_token.clone()),
+                        Some(tokens.refresh_token.clone()),
+                    )
+                    .await
+                    {
+                        eprintln!("Persist error: {err}");
+                        return HandledRequest::Response(
+                            Response::from_string(format!("Unable to persist auth file: {err}"))
                                 .with_status_code(500),
                         );
                     }
+
+                    let success_url = compose_success_url(
+                        actual_port,
+                        &opts.issuer,
+                        &tokens.id_token,
+                        &tokens.access_token,
+                    );
+                    match tiny_http::Header::from_bytes(&b"Location"[..], success_url.as_bytes()) {
+                        Ok(header) => HandledRequest::RedirectWithHeader(header),
+                        Err(_) => HandledRequest::Response(
+                            Response::from_string("Internal Server Error").with_status_code(500),
+                        ),
+                    }
                 }
-            }
-            "/success" => {
-                let body = include_str!("assets/success.html");
-                let mut resp = Response::from_data(body.as_bytes());
-                if let Ok(h) = tiny_http::Header::from_bytes(
-                    &b"Content-Type"[..],
-                    &b"text/html; charset=utf-8"[..],
-                ) {
-                    resp.add_header(h);
+                Err(err) => {
+                    eprintln!("Token exchange error: {err}");
+                    HandledRequest::Response(
+                        Response::from_string(format!("Token exchange failed: {err}"))
+                            .with_status_code(500),
+                    )
                 }
-                let _ = req.respond(resp);
-                shutdown_flag.store(true, Ordering::SeqCst);
-            }
-            _ => {
-                let _ = req.respond(Response::from_string("Not Found").with_status_code(404));
             }
         }
+        "/success" => {
+            let body = include_str!("assets/success.html");
+            let mut resp = Response::from_data(body.as_bytes());
+            if let Ok(h) = tiny_http::Header::from_bytes(
+                &b"Content-Type"[..],
+                &b"text/html; charset=utf-8"[..],
+            ) {
+                resp.add_header(h);
+            }
+            HandledRequest::ResponseAndExit(resp)
+        }
+        _ => HandledRequest::Response(Response::from_string("Not Found").with_status_code(404)),
     }
-
-    Ok(())
 }
 
 fn build_authorize_url(
@@ -240,7 +309,7 @@ struct ExchangedTokens {
     refresh_token: String,
 }
 
-fn exchange_code_for_tokens(
+async fn exchange_code_for_tokens(
     issuer: &str,
     client_id: &str,
     redirect_uri: &str,
@@ -254,7 +323,7 @@ fn exchange_code_for_tokens(
         refresh_token: String,
     }
 
-    let client = reqwest::blocking::Client::new();
+    let client = reqwest::Client::new();
     let resp = client
         .post(format!("{issuer}/oauth/token"))
         .header("Content-Type", "application/x-www-form-urlencoded")
@@ -266,6 +335,7 @@ fn exchange_code_for_tokens(
             urlencoding::encode(&pkce.code_verifier)
         ))
         .send()
+        .await
         .map_err(io::Error::other)?;
 
     if !resp.status().is_success() {
@@ -275,7 +345,7 @@ fn exchange_code_for_tokens(
         )));
     }
 
-    let tokens: TokenResponse = resp.json().map_err(io::Error::other)?;
+    let tokens: TokenResponse = resp.json().await.map_err(io::Error::other)?;
     Ok(ExchangedTokens {
         id_token: tokens.id_token,
         access_token: tokens.access_token,
@@ -283,43 +353,49 @@ fn exchange_code_for_tokens(
     })
 }
 
-fn persist_tokens(
+async fn persist_tokens_async(
     codex_home: &Path,
     api_key: Option<String>,
     id_token: String,
     access_token: Option<String>,
     refresh_token: Option<String>,
 ) -> io::Result<()> {
-    let auth_file = get_auth_file(codex_home);
-    if let Some(parent) = auth_file.parent() {
-        if !parent.exists() {
+    // Reuse existing synchronous logic but run it off the async runtime.
+    let codex_home = codex_home.to_path_buf();
+    tokio::task::spawn_blocking(move || {
+        let auth_file = get_auth_file(&codex_home);
+        if let Some(parent) = auth_file.parent()
+            && !parent.exists()
+        {
             std::fs::create_dir_all(parent).map_err(io::Error::other)?;
         }
-    }
 
-    let mut auth = read_or_default(&auth_file);
-    if let Some(key) = api_key {
-        auth.openai_api_key = Some(key);
-    }
-    let tokens = auth
-        .tokens
-        .get_or_insert_with(crate::token_data::TokenData::default);
-    tokens.id_token = crate::token_data::parse_id_token(&id_token).map_err(io::Error::other)?;
-    // Persist chatgpt_account_id if present in claims
-    if let Some(acc) = jwt_auth_claims(&id_token)
-        .get("chatgpt_account_id")
-        .and_then(|v| v.as_str())
-    {
-        tokens.account_id = Some(acc.to_string());
-    }
-    if let Some(at) = access_token {
-        tokens.access_token = at;
-    }
-    if let Some(rt) = refresh_token {
-        tokens.refresh_token = rt;
-    }
-    auth.last_refresh = Some(Utc::now());
-    super::write_auth_json(&auth_file, &auth)
+        let mut auth = read_or_default(&auth_file);
+        if let Some(key) = api_key {
+            auth.openai_api_key = Some(key);
+        }
+        let tokens = auth
+            .tokens
+            .get_or_insert_with(crate::token_data::TokenData::default);
+        tokens.id_token = crate::token_data::parse_id_token(&id_token).map_err(io::Error::other)?;
+        // Persist chatgpt_account_id if present in claims
+        if let Some(acc) = jwt_auth_claims(&id_token)
+            .get("chatgpt_account_id")
+            .and_then(|v| v.as_str())
+        {
+            tokens.account_id = Some(acc.to_string());
+        }
+        if let Some(at) = access_token {
+            tokens.access_token = at;
+        }
+        if let Some(rt) = refresh_token {
+            tokens.refresh_token = rt;
+        }
+        auth.last_refresh = Some(Utc::now());
+        super::write_auth_json(&auth_file, &auth)
+    })
+    .await
+    .map_err(|e| io::Error::other(format!("persist task failed: {e}")))?
 }
 
 fn read_or_default(path: &Path) -> AuthDotJson {
@@ -412,13 +488,13 @@ fn jwt_auth_claims(jwt: &str) -> serde_json::Map<String, serde_json::Value> {
     serde_json::Map::new()
 }
 
-fn obtain_api_key(issuer: &str, client_id: &str, id_token: &str) -> io::Result<String> {
+async fn obtain_api_key(issuer: &str, client_id: &str, id_token: &str) -> io::Result<String> {
     // Token exchange for an API key access token
     #[derive(serde::Deserialize)]
     struct ExchangeResp {
         access_token: String,
     }
-    let client = reqwest::blocking::Client::new();
+    let client = reqwest::Client::new();
     let resp = client
         .post(format!("{issuer}/oauth/token"))
         .header("Content-Type", "application/x-www-form-urlencoded")
@@ -431,6 +507,7 @@ fn obtain_api_key(issuer: &str, client_id: &str, id_token: &str) -> io::Result<S
             urlencoding::encode("urn:ietf:params:oauth:token-type:id_token")
         ))
         .send()
+        .await
         .map_err(io::Error::other)?;
     if !resp.status().is_success() {
         return Err(io::Error::other(format!(
@@ -438,6 +515,6 @@ fn obtain_api_key(issuer: &str, client_id: &str, id_token: &str) -> io::Result<S
             resp.status()
         )));
     }
-    let body: ExchangeResp = resp.json().map_err(io::Error::other)?;
+    let body: ExchangeResp = resp.json().await.map_err(io::Error::other)?;
     Ok(body.access_token)
 }

codex-rs/login/src/token_data.rs

@@ -3,6 +3,8 @@ use serde::Deserialize;
 use serde::Serialize;
 use thiserror::Error;
 
+use crate::AuthMode;
+
 #[derive(Deserialize, Serialize, Clone, Debug, PartialEq, Default)]
 pub struct TokenData {
     /// Flat info parsed from the JWT in auth.json.
@@ -23,12 +25,31 @@ pub struct TokenData {
 impl TokenData {
     /// Returns true if this is a plan that should use the traditional
     /// "metered" billing via an API key.
-    pub(crate) fn is_plan_that_should_use_api_key(&self) -> bool {
+    pub(crate) fn should_use_api_key(
+        &self,
+        preferred_auth_method: AuthMode,
+        is_openai_email: bool,
+    ) -> bool {
+        if preferred_auth_method == AuthMode::ApiKey {
+            return true;
+        }
+        // If the email is an OpenAI email, use AuthMode::ChatGPT unless preferred_auth_method is AuthMode::ApiKey.
+        if is_openai_email {
+            return false;
+        }
+
         self.id_token
             .chatgpt_plan_type
             .as_ref()
             .is_none_or(|plan| plan.is_plan_that_should_use_api_key())
     }
+
+    pub fn is_openai_email(&self) -> bool {
+        self.id_token
+            .email
+            .as_deref()
+            .is_some_and(|email| email.trim().to_ascii_lowercase().ends_with("@openai.com"))
+    }
 }
 
 /// Flat subset of useful claims in id_token from auth.json.

codex-rs/login/tests/login_server_e2e.rs

@@ -1,12 +1,11 @@
-#![expect(clippy::unwrap_used)]
+#![allow(clippy::unwrap_used)]
 use std::net::SocketAddr;
 use std::net::TcpListener;
 use std::thread;
 
 use base64::Engine;
-use codex_login::LoginServerInfo;
 use codex_login::ServerOptions;
-use codex_login::run_server_blocking_with_notify;
+use codex_login::run_login_server;
 use tempfile::tempdir;
 
 // See spawn.rs for details
@@ -74,8 +73,8 @@ fn start_mock_issuer() -> (SocketAddr, thread::JoinHandle<()>) {
     (addr, handle)
 }
 
-#[test]
-fn end_to_end_login_flow_persists_auth_json() {
+#[tokio::test]
+async fn end_to_end_login_flow_persists_auth_json() {
     if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
         println!(
             "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
@@ -94,35 +93,28 @@ fn end_to_end_login_flow_persists_auth_json() {
     // Run server in background
     let server_home = codex_home.clone();
 
-    let (tx, rx) = std::sync::mpsc::channel::<LoginServerInfo>();
-    let server_thread = thread::spawn(move || {
-        let opts = ServerOptions {
-            codex_home: &server_home,
-            client_id: codex_login::CLIENT_ID,
-            issuer: &issuer,
-            port: 0,
-            open_browser: false,
-            force_state: Some(state),
-        };
-        run_server_blocking_with_notify(opts, Some(tx), None).unwrap();
-    });
-
-    let server_info = rx.recv().unwrap();
-    let login_port = server_info.actual_port;
+    let opts = ServerOptions {
+        codex_home: server_home,
+        client_id: codex_login::CLIENT_ID.to_string(),
+        issuer,
+        port: 0,
+        open_browser: false,
+        force_state: Some(state),
+    };
+    let server = run_login_server(opts).unwrap();
+    let login_port = server.actual_port;
 
     // Simulate browser callback, and follow redirect to /success
-    let client = reqwest::blocking::Client::builder()
+    let client = reqwest::Client::builder()
         .redirect(reqwest::redirect::Policy::limited(5))
         .build()
         .unwrap();
     let url = format!("http://127.0.0.1:{login_port}/auth/callback?code=abc&state=test_state_123");
-    let resp = client.get(&url).send().unwrap();
+    let resp = client.get(&url).send().await.unwrap();
     assert!(resp.status().is_success());
 
     // Wait for server shutdown
-    server_thread
-        .join()
-        .unwrap_or_else(|_| panic!("server thread panicked"));
+    server.block_until_done().await.unwrap();
 
     // Validate auth.json
     let auth_path = codex_home.join("auth.json");
@@ -140,8 +132,8 @@ fn end_to_end_login_flow_persists_auth_json() {
     drop(issuer_handle);
 }
 
-#[test]
-fn creates_missing_codex_home_dir() {
+#[tokio::test]
+async fn creates_missing_codex_home_dir() {
     if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
         println!(
             "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
@@ -159,30 +151,23 @@ fn creates_missing_codex_home_dir() {
 
     // Run server in background
     let server_home = codex_home.clone();
-    let (tx, rx) = std::sync::mpsc::channel::<LoginServerInfo>();
-    let server_thread = thread::spawn(move || {
-        let opts = ServerOptions {
-            codex_home: &server_home,
-            client_id: codex_login::CLIENT_ID,
-            issuer: &issuer,
-            port: 0,
-            open_browser: false,
-            force_state: Some(state),
-        };
-        run_server_blocking_with_notify(opts, Some(tx), None).unwrap()
-    });
+    let opts = ServerOptions {
+        codex_home: server_home,
+        client_id: codex_login::CLIENT_ID.to_string(),
+        issuer,
+        port: 0,
+        open_browser: false,
+        force_state: Some(state),
+    };
+    let server = run_login_server(opts).unwrap();
+    let login_port = server.actual_port;
 
-    let server_info = rx.recv().unwrap();
-    let login_port = server_info.actual_port;
-
-    let client = reqwest::blocking::Client::new();
+    let client = reqwest::Client::new();
     let url = format!("http://127.0.0.1:{login_port}/auth/callback?code=abc&state=state2");
-    let resp = client.get(&url).send().unwrap();
+    let resp = client.get(&url).send().await.unwrap();
     assert!(resp.status().is_success());
 
-    server_thread
-        .join()
-        .unwrap_or_else(|_| panic!("server thread panicked"));
+    server.block_until_done().await.unwrap();
 
     let auth_path = codex_home.join("auth.json");
     assert!(

codex-rs/mcp-server/Cargo.toml

@@ -17,7 +17,10 @@ workspace = true
 [dependencies]
 anyhow = "1"
 codex-arg0 = { path = "../arg0" }
+codex-common = { path = "../common", features = ["cli"] }
 codex-core = { path = "../core" }
+codex-login = { path = "../login" }
+codex-protocol = { path = "../protocol" }
 mcp-types = { path = "../mcp-types" }
 schemars = "0.8.22"
 serde = { version = "1", features = ["derive"] }

codex-rs/mcp-server/src/codex_message_processor.rs

@@ -1,19 +1,25 @@
 use std::collections::HashMap;
 use std::path::PathBuf;
 use std::sync::Arc;
+use std::time::Duration;
 
 use codex_core::CodexConversation;
 use codex_core::ConversationManager;
 use codex_core::NewConversation;
 use codex_core::config::Config;
 use codex_core::config::ConfigOverrides;
+use codex_core::git_info::git_diff_to_remote;
 use codex_core::protocol::ApplyPatchApprovalRequestEvent;
 use codex_core::protocol::Event;
 use codex_core::protocol::EventMsg;
 use codex_core::protocol::ExecApprovalRequestEvent;
 use codex_core::protocol::ReviewDecision;
+use codex_login::AuthManager;
+use codex_protocol::mcp_protocol::AuthMode;
+use codex_protocol::mcp_protocol::GitDiffToRemoteResponse;
 use mcp_types::JSONRPCErrorError;
 use mcp_types::RequestId;
+use tokio::sync::Mutex;
 use tokio::sync::oneshot;
 use tracing::error;
 use uuid::Uuid;
@@ -23,47 +29,82 @@ use crate::error_code::INVALID_REQUEST_ERROR_CODE;
 use crate::json_to_toml::json_to_toml;
 use crate::outgoing_message::OutgoingMessageSender;
 use crate::outgoing_message::OutgoingNotification;
-use crate::wire_format::APPLY_PATCH_APPROVAL_METHOD;
-use crate::wire_format::AddConversationListenerParams;
-use crate::wire_format::AddConversationSubscriptionResponse;
-use crate::wire_format::ApplyPatchApprovalParams;
-use crate::wire_format::ApplyPatchApprovalResponse;
-use crate::wire_format::ClientRequest;
-use crate::wire_format::ConversationId;
-use crate::wire_format::EXEC_COMMAND_APPROVAL_METHOD;
-use crate::wire_format::ExecCommandApprovalParams;
-use crate::wire_format::ExecCommandApprovalResponse;
-use crate::wire_format::InputItem as WireInputItem;
-use crate::wire_format::InterruptConversationParams;
-use crate::wire_format::InterruptConversationResponse;
-use crate::wire_format::NewConversationParams;
-use crate::wire_format::NewConversationResponse;
-use crate::wire_format::RemoveConversationListenerParams;
-use crate::wire_format::RemoveConversationSubscriptionResponse;
-use crate::wire_format::SendUserMessageParams;
-use crate::wire_format::SendUserMessageResponse;
 use codex_core::protocol::InputItem as CoreInputItem;
 use codex_core::protocol::Op;
+use codex_login::CLIENT_ID;
+use codex_login::ServerOptions as LoginServerOptions;
+use codex_login::ShutdownHandle;
+use codex_login::run_login_server;
+use codex_protocol::mcp_protocol::APPLY_PATCH_APPROVAL_METHOD;
+use codex_protocol::mcp_protocol::AddConversationListenerParams;
+use codex_protocol::mcp_protocol::AddConversationSubscriptionResponse;
+use codex_protocol::mcp_protocol::ApplyPatchApprovalParams;
+use codex_protocol::mcp_protocol::ApplyPatchApprovalResponse;
+use codex_protocol::mcp_protocol::AuthStatusChangeNotification;
+use codex_protocol::mcp_protocol::ClientRequest;
+use codex_protocol::mcp_protocol::ConversationId;
+use codex_protocol::mcp_protocol::EXEC_COMMAND_APPROVAL_METHOD;
+use codex_protocol::mcp_protocol::ExecCommandApprovalParams;
+use codex_protocol::mcp_protocol::ExecCommandApprovalResponse;
+use codex_protocol::mcp_protocol::InputItem as WireInputItem;
+use codex_protocol::mcp_protocol::InterruptConversationParams;
+use codex_protocol::mcp_protocol::InterruptConversationResponse;
+use codex_protocol::mcp_protocol::LoginChatGptCompleteNotification;
+use codex_protocol::mcp_protocol::LoginChatGptResponse;
+use codex_protocol::mcp_protocol::NewConversationParams;
+use codex_protocol::mcp_protocol::NewConversationResponse;
+use codex_protocol::mcp_protocol::RemoveConversationListenerParams;
+use codex_protocol::mcp_protocol::RemoveConversationSubscriptionResponse;
+use codex_protocol::mcp_protocol::SendUserMessageParams;
+use codex_protocol::mcp_protocol::SendUserMessageResponse;
+use codex_protocol::mcp_protocol::SendUserTurnParams;
+use codex_protocol::mcp_protocol::SendUserTurnResponse;
+use codex_protocol::mcp_protocol::ServerNotification;
+
+// Duration before a ChatGPT login attempt is abandoned.
+const LOGIN_CHATGPT_TIMEOUT: Duration = Duration::from_secs(10 * 60);
+
+struct ActiveLogin {
+    shutdown_handle: ShutdownHandle,
+    login_id: Uuid,
+}
+
+impl ActiveLogin {
+    fn drop(&self) {
+        self.shutdown_handle.shutdown();
+    }
+}
 
 /// Handles JSON-RPC messages for Codex conversations.
 pub(crate) struct CodexMessageProcessor {
+    auth_manager: Arc<AuthManager>,
     conversation_manager: Arc<ConversationManager>,
     outgoing: Arc<OutgoingMessageSender>,
     codex_linux_sandbox_exe: Option<PathBuf>,
+    config: Arc<Config>,
     conversation_listeners: HashMap<Uuid, oneshot::Sender<()>>,
+    active_login: Arc<Mutex<Option<ActiveLogin>>>,
+    // Queue of pending interrupt requests per conversation. We reply when TurnAborted arrives.
+    pending_interrupts: Arc<Mutex<HashMap<Uuid, Vec<RequestId>>>>,
 }
 
 impl CodexMessageProcessor {
     pub fn new(
+        auth_manager: Arc<AuthManager>,
         conversation_manager: Arc<ConversationManager>,
         outgoing: Arc<OutgoingMessageSender>,
         codex_linux_sandbox_exe: Option<PathBuf>,
+        config: Arc<Config>,
     ) -> Self {
         Self {
+            auth_manager,
             conversation_manager,
             outgoing,
             codex_linux_sandbox_exe,
+            config,
             conversation_listeners: HashMap::new(),
+            active_login: Arc::new(Mutex::new(None)),
+            pending_interrupts: Arc::new(Mutex::new(HashMap::new())),
         }
     }
 
@@ -78,6 +119,9 @@ impl CodexMessageProcessor {
             ClientRequest::SendUserMessage { request_id, params } => {
                 self.send_user_message(request_id, params).await;
             }
+            ClientRequest::SendUserTurn { request_id, params } => {
+                self.send_user_turn(request_id, params).await;
+            }
             ClientRequest::InterruptConversation { request_id, params } => {
                 self.interrupt_conversation(request_id, params).await;
             }
@@ -87,9 +131,229 @@ impl CodexMessageProcessor {
             ClientRequest::RemoveConversationListener { request_id, params } => {
                 self.remove_conversation_listener(request_id, params).await;
             }
+            ClientRequest::GitDiffToRemote { request_id, params } => {
+                self.git_diff_to_origin(request_id, params.cwd).await;
+            }
+            ClientRequest::LoginChatGpt { request_id } => {
+                self.login_chatgpt(request_id).await;
+            }
+            ClientRequest::CancelLoginChatGpt { request_id, params } => {
+                self.cancel_login_chatgpt(request_id, params.login_id).await;
+            }
+            ClientRequest::LogoutChatGpt { request_id } => {
+                self.logout_chatgpt(request_id).await;
+            }
+            ClientRequest::GetAuthStatus { request_id, params } => {
+                self.get_auth_status(request_id, params).await;
+            }
         }
     }
 
+    async fn login_chatgpt(&mut self, request_id: RequestId) {
+        let config = self.config.as_ref();
+
+        let opts = LoginServerOptions {
+            open_browser: false,
+            ..LoginServerOptions::new(config.codex_home.clone(), CLIENT_ID.to_string())
+        };
+
+        enum LoginChatGptReply {
+            Response(LoginChatGptResponse),
+            Error(JSONRPCErrorError),
+        }
+
+        let reply = match run_login_server(opts) {
+            Ok(server) => {
+                let login_id = Uuid::new_v4();
+                let shutdown_handle = server.cancel_handle();
+
+                // Replace active login if present.
+                {
+                    let mut guard = self.active_login.lock().await;
+                    if let Some(existing) = guard.take() {
+                        existing.drop();
+                    }
+                    *guard = Some(ActiveLogin {
+                        shutdown_handle: shutdown_handle.clone(),
+                        login_id,
+                    });
+                }
+
+                let response = LoginChatGptResponse {
+                    login_id,
+                    auth_url: server.auth_url.clone(),
+                };
+
+                // Spawn background task to monitor completion.
+                let outgoing_clone = self.outgoing.clone();
+                let active_login = self.active_login.clone();
+                let auth_manager = self.auth_manager.clone();
+                tokio::spawn(async move {
+                    let (success, error_msg) = match tokio::time::timeout(
+                        LOGIN_CHATGPT_TIMEOUT,
+                        server.block_until_done(),
+                    )
+                    .await
+                    {
+                        Ok(Ok(())) => (true, None),
+                        Ok(Err(err)) => (false, Some(format!("Login server error: {err}"))),
+                        Err(_elapsed) => {
+                            // Timeout: cancel server and report
+                            shutdown_handle.shutdown();
+                            (false, Some("Login timed out".to_string()))
+                        }
+                    };
+                    let payload = LoginChatGptCompleteNotification {
+                        login_id,
+                        success,
+                        error: error_msg,
+                    };
+                    outgoing_clone
+                        .send_server_notification(ServerNotification::LoginChatGptComplete(payload))
+                        .await;
+
+                    // Send an auth status change notification.
+                    if success {
+                        // Update in-memory auth cache now that login completed.
+                        auth_manager.reload();
+
+                        // Notify clients with the actual current auth mode.
+                        let current_auth_method = auth_manager.auth().map(|a| a.mode);
+                        let payload = AuthStatusChangeNotification {
+                            auth_method: current_auth_method,
+                        };
+                        outgoing_clone
+                            .send_server_notification(ServerNotification::AuthStatusChange(payload))
+                            .await;
+                    }
+
+                    // Clear the active login if it matches this attempt. It may have been replaced or cancelled.
+                    let mut guard = active_login.lock().await;
+                    if guard.as_ref().map(|l| l.login_id) == Some(login_id) {
+                        *guard = None;
+                    }
+                });
+
+                LoginChatGptReply::Response(response)
+            }
+            Err(err) => LoginChatGptReply::Error(JSONRPCErrorError {
+                code: INTERNAL_ERROR_CODE,
+                message: format!("failed to start login server: {err}"),
+                data: None,
+            }),
+        };
+
+        match reply {
+            LoginChatGptReply::Response(resp) => {
+                self.outgoing.send_response(request_id, resp).await
+            }
+            LoginChatGptReply::Error(err) => self.outgoing.send_error(request_id, err).await,
+        }
+    }
+
+    async fn cancel_login_chatgpt(&mut self, request_id: RequestId, login_id: Uuid) {
+        let mut guard = self.active_login.lock().await;
+        if guard.as_ref().map(|l| l.login_id) == Some(login_id) {
+            if let Some(active) = guard.take() {
+                active.drop();
+            }
+            drop(guard);
+            self.outgoing
+                .send_response(
+                    request_id,
+                    codex_protocol::mcp_protocol::CancelLoginChatGptResponse {},
+                )
+                .await;
+        } else {
+            drop(guard);
+            let error = JSONRPCErrorError {
+                code: INVALID_REQUEST_ERROR_CODE,
+                message: format!("login id not found: {login_id}"),
+                data: None,
+            };
+            self.outgoing.send_error(request_id, error).await;
+        }
+    }
+
+    async fn logout_chatgpt(&mut self, request_id: RequestId) {
+        {
+            // Cancel any active login attempt.
+            let mut guard = self.active_login.lock().await;
+            if let Some(active) = guard.take() {
+                active.drop();
+            }
+        }
+
+        if let Err(err) = self.auth_manager.logout() {
+            let error = JSONRPCErrorError {
+                code: INTERNAL_ERROR_CODE,
+                message: format!("logout failed: {err}"),
+                data: None,
+            };
+            self.outgoing.send_error(request_id, error).await;
+            return;
+        }
+
+        self.outgoing
+            .send_response(
+                request_id,
+                codex_protocol::mcp_protocol::LogoutChatGptResponse {},
+            )
+            .await;
+
+        // Send auth status change notification reflecting the current auth mode
+        // after logout (which may fall back to API key via env var).
+        let current_auth_method = self.auth_manager.auth().map(|auth| auth.mode);
+        let payload = AuthStatusChangeNotification {
+            auth_method: current_auth_method,
+        };
+        self.outgoing
+            .send_server_notification(ServerNotification::AuthStatusChange(payload))
+            .await;
+    }
+
+    async fn get_auth_status(
+        &self,
+        request_id: RequestId,
+        params: codex_protocol::mcp_protocol::GetAuthStatusParams,
+    ) {
+        let preferred_auth_method: AuthMode = self.auth_manager.preferred_auth_method();
+        let include_token = params.include_token.unwrap_or(false);
+        let do_refresh = params.refresh_token.unwrap_or(false);
+
+        if do_refresh && let Err(err) = self.auth_manager.refresh_token().await {
+            tracing::warn!("failed to refresh token while getting auth status: {err}");
+        }
+
+        let response = match self.auth_manager.auth() {
+            Some(auth) => {
+                let (reported_auth_method, token_opt) = match auth.get_token().await {
+                    Ok(token) if !token.is_empty() => {
+                        let tok = if include_token { Some(token) } else { None };
+                        (Some(auth.mode), tok)
+                    }
+                    Ok(_) => (None, None),
+                    Err(err) => {
+                        tracing::warn!("failed to get token for auth status: {err}");
+                        (None, None)
+                    }
+                };
+                codex_protocol::mcp_protocol::GetAuthStatusResponse {
+                    auth_method: reported_auth_method,
+                    preferred_auth_method,
+                    auth_token: token_opt,
+                }
+            }
+            None => codex_protocol::mcp_protocol::GetAuthStatusResponse {
+                auth_method: None,
+                preferred_auth_method,
+                auth_token: None,
+            },
+        };
+
+        self.outgoing.send_response(request_id, response).await;
+    }
+
     async fn process_new_conversation(&self, request_id: RequestId, params: NewConversationParams) {
         let config = match derive_config_from_params(params, self.codex_linux_sandbox_exe.clone()) {
             Ok(config) => config,
@@ -169,6 +433,58 @@ impl CodexMessageProcessor {
             .await;
     }
 
+    async fn send_user_turn(&self, request_id: RequestId, params: SendUserTurnParams) {
+        let SendUserTurnParams {
+            conversation_id,
+            items,
+            cwd,
+            approval_policy,
+            sandbox_policy,
+            model,
+            effort,
+            summary,
+        } = params;
+
+        let Ok(conversation) = self
+            .conversation_manager
+            .get_conversation(conversation_id.0)
+            .await
+        else {
+            let error = JSONRPCErrorError {
+                code: INVALID_REQUEST_ERROR_CODE,
+                message: format!("conversation not found: {conversation_id}"),
+                data: None,
+            };
+            self.outgoing.send_error(request_id, error).await;
+            return;
+        };
+
+        let mapped_items: Vec<CoreInputItem> = items
+            .into_iter()
+            .map(|item| match item {
+                WireInputItem::Text { text } => CoreInputItem::Text { text },
+                WireInputItem::Image { image_url } => CoreInputItem::Image { image_url },
+                WireInputItem::LocalImage { path } => CoreInputItem::LocalImage { path },
+            })
+            .collect();
+
+        let _ = conversation
+            .submit(Op::UserTurn {
+                items: mapped_items,
+                cwd,
+                approval_policy,
+                sandbox_policy,
+                model,
+                effort,
+                summary,
+            })
+            .await;
+
+        self.outgoing
+            .send_response(request_id, SendUserTurnResponse {})
+            .await;
+    }
+
     async fn interrupt_conversation(
         &mut self,
         request_id: RequestId,
@@ -189,13 +505,14 @@ impl CodexMessageProcessor {
             return;
         };
 
-        let _ = conversation.submit(Op::Interrupt).await;
+        // Record the pending interrupt so we can reply when TurnAborted arrives.
+        {
+            let mut map = self.pending_interrupts.lock().await;
+            map.entry(conversation_id.0).or_default().push(request_id);
+        }
 
-        // Apparently CodexConversation does not send an ack for Op::Interrupt,
-        // so we can reply to the request right away.
-        self.outgoing
-            .send_response(request_id, InterruptConversationResponse {})
-            .await;
+        // Submit the interrupt; we'll respond upon TurnAborted.
+        let _ = conversation.submit(Op::Interrupt).await;
     }
 
     async fn add_conversation_listener(
@@ -223,6 +540,7 @@ impl CodexMessageProcessor {
         self.conversation_listeners
             .insert(subscription_id, cancel_tx);
         let outgoing_for_task = self.outgoing.clone();
+        let pending_interrupts = self.pending_interrupts.clone();
         tokio::spawn(async move {
             loop {
                 tokio::select! {
@@ -263,7 +581,7 @@ impl CodexMessageProcessor {
                         })
                         .await;
 
-                        apply_bespoke_event_handling(event, conversation_id, conversation.clone(), outgoing_for_task.clone()).await;
+                        apply_bespoke_event_handling(event.clone(), conversation_id, conversation.clone(), outgoing_for_task.clone(), pending_interrupts.clone()).await;
                     }
                 }
             }
@@ -295,6 +613,27 @@ impl CodexMessageProcessor {
             }
         }
     }
+
+    async fn git_diff_to_origin(&self, request_id: RequestId, cwd: PathBuf) {
+        let diff = git_diff_to_remote(&cwd).await;
+        match diff {
+            Some(value) => {
+                let response = GitDiffToRemoteResponse {
+                    sha: value.sha,
+                    diff: value.diff,
+                };
+                self.outgoing.send_response(request_id, response).await;
+            }
+            None => {
+                let error = JSONRPCErrorError {
+                    code: INVALID_REQUEST_ERROR_CODE,
+                    message: format!("failed to compute git diff to remote for cwd: {cwd:?}"),
+                    data: None,
+                };
+                self.outgoing.send_error(request_id, error).await;
+            }
+        }
+    }
 }
 
 async fn apply_bespoke_event_handling(
@@ -302,6 +641,7 @@ async fn apply_bespoke_event_handling(
     conversation_id: ConversationId,
     conversation: Arc<CodexConversation>,
     outgoing: Arc<OutgoingMessageSender>,
+    pending_interrupts: Arc<Mutex<HashMap<Uuid, Vec<RequestId>>>>,
 ) {
     let Event { id: event_id, msg } = event;
     match msg {
@@ -350,6 +690,22 @@ async fn apply_bespoke_event_handling(
                 on_exec_approval_response(event_id, rx, conversation).await;
             });
         }
+        // If this is a TurnAborted, reply to any pending interrupt requests.
+        EventMsg::TurnAborted(turn_aborted_event) => {
+            let pending = {
+                let mut map = pending_interrupts.lock().await;
+                map.remove(&conversation_id.0).unwrap_or_default()
+            };
+            if !pending.is_empty() {
+                let response = InterruptConversationResponse {
+                    abort_reason: turn_aborted_event.reason,
+                };
+                for rid in pending {
+                    outgoing.send_response(rid, response.clone()).await;
+                }
+            }
+        }
+
         _ => {}
     }
 }
@@ -363,21 +719,23 @@ fn derive_config_from_params(
         profile,
         cwd,
         approval_policy,
-        sandbox,
+        sandbox: sandbox_mode,
         config: cli_overrides,
         base_instructions,
         include_plan_tool,
+        include_apply_patch_tool,
     } = params;
     let overrides = ConfigOverrides {
         model,
         config_profile: profile,
         cwd: cwd.map(PathBuf::from),
-        approval_policy: approval_policy.map(Into::into),
-        sandbox_mode: sandbox.map(Into::into),
+        approval_policy,
+        sandbox_mode,
         model_provider: None,
         codex_linux_sandbox_exe,
         base_instructions,
         include_plan_tool,
+        include_apply_patch_tool,
         disable_response_storage: None,
         show_raw_agent_reasoning: None,
     };